SkillAgentSearch skills...

ln-33-plan-reviewer

Reviews a concrete implementation plan for missing decisions, feasibility and risk before execution; read-only.

Install / Use

npx skills add levnikolaevich/claude-code-skills --skill ln-33-plan-reviewer

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

82/100

Category

Legal

Supported Platforms

Universal

Our assessment of ln-33-plan-reviewer

ln-33-plan-reviewer scores 82/100 on our quality scale, 167th of 210 Legal skills we index.

Its SKILL.md is 25 KB long, well organised into 12 sections and no code examples: a thorough specification that gives an agent plenty to work with.

It has 566 GitHub stars, a meaningful sign that others use it.

Substance
30/30
Structure
13/20
Description
12/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so ln-33-plan-reviewer is actively maintained.
  • Our last check on 2026-11-08 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-15. Automated pattern scan on 2026-10-15. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

ln-33-plan-reviewer compared with similar skills

All 4 of these similar skills score higher than ln-33-plan-reviewer; compare them before choosing.

SkillScoreStarsUpdatedFormat
ln-33-plan-reviewer (this skill)by levnikolaevich825662mo agoSKILL.md
algorithmic-artby anthropics100177.9k57d agoSKILL.md
pptxby anthropics100177.9k57d agoSKILL.md
prospectingby coreyhaines3110060.1k7d agoSKILL.md
ad-creativeby coreyhaines3110060.1k7d agoSKILL.md

Frequently asked questions

How do I install ln-33-plan-reviewer?
Run npx skills add levnikolaevich/claude-code-skills --skill ln-33-plan-reviewer. The install tabs above show the steps for each supported agent.
Which AI agents does ln-33-plan-reviewer work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is ln-33-plan-reviewer safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is ln-33-plan-reviewer still maintained?
The repository was last updated about 2 months ago, so ln-33-plan-reviewer is actively maintained.

name: ln-33-plan-reviewer description: "Reviews a concrete implementation plan for missing decisions, feasibility and risk before execution; read-only."

Plan Reviewer

Goal: Perform a read-only, evidence-first second pass over an implementation plan. Verify the plan; do not execute it. A strong result is decision-complete, grounded in the actual repository, explicit about uncertainty, no more complex than the problem requires, and expressed in the fewest words and execution steps that preserve safety.

Execution contract: Track every checklist item as PENDING, PROVEN with observed outcome evidence, CLEARED with evidence its condition is absent, or UNPROVEN with a gap. Reading, delegation, tool failure, zero exit status, and self-reported success are not proof. Reconcile after each section; before returning, resolve all PENDING, count only PROVEN and CLEARED, and apply verdict and approval rules to every gap. Preserve intent, scope, mode, and existing authorization. Complete authorized work before required external approval; ask only consequential unresolved choices. If nobody can answer, report the exact question and apply the skill's gap verdict without waiting or guessing. Cite any blocking instruction and unresolved boundary; never invent approval gates. Scale depth to material risk; preserve mandatory checks, dependencies, and safety order while choosing verification methods. Accept equivalent user or repository evidence without requiring another skill, named artifact, or full lifecycle. Preserve source requirement and decision IDs. Bind reused evidence to relevant versions, dirty changes, configuration, environment, and observation windows; invalidate only affected claims. Choose the primary workflow by outcome and explicit selection. Consume neighboring contracts and valid evidence without duplicating ownership or restarting audits. Split distinct deliverables by scope, not mandatory skill invocation. Broad independent assessments use audit workflows; focused domain reviews remain read-only. On continuation, reconcile task, authorization, state, and gaps. Return a compact continuation record for long work or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Before retrieval, define the evidence question; read selectively without skipping applicable instructions. Use tools for mechanical processing; summarize bounded results, errors, coverage, and source paths, keeping full output outside context. Before technical decisions, establish applicability and actual versions; verify version-dependent assumptions against official documentation or specifications. Search and read primary pages for current external recommendations; snippets are not evidence. Version-matched bundled documentation or valid prior evidence suffices. Record decision, version, source, and limitations. Mark unavailable evidence UNVERIFIED; block only essential dependent work. Prefer native mechanisms, justify added tools or abstractions with evidence, and reuse the existing rule owner.

Tool Routing

| Need | Preferred tool | Use it when | Fallback | |---|---|---|---| | Repository instructions and current state | Native file read plus Git | Always read the active host's applicable repository instructions; use git status, diff, and history when branch or change context matters | Equivalent host file and shell tools | | Paths, text, config, docs, and focused code reads | Native file listing, search, outline, and range reads | The question is textual or structural and does not require symbol identity | Narrow the path and pattern before expanding content | | Symbols, references, callers, implementations, cycles, and blast radius | Language server or host-native code intelligence | A plan changes existing code relationships, public APIs, module boundaries, or architecture | Targeted search plus direct inspection of definitions and consumers | | Planned edit risk | Code intelligence plus caller and consumer search | The plan names an edit region, route, event, response contract, or existing change surface | Inspect named symbols and adjacent integration points manually | | Build, test, migration, and script feasibility | Repository-defined commands through the shell | The plan depends on a command, baseline, generated artifact, or existing test surface being available | Inspect scripts and CI configuration; mark execution unverified | | Correction and external-claim research | Official vendor documentation, specifications, or standards through documentation search or the web | External behavior or a correction depends on changing platform semantics | Reputable primary engineering material; otherwise mark the claim or correction UNVERIFIED | | Independent challenge | Native subagents in separate contexts | A plan benefits from execution, fresh-context, or adversarial perspective | Run the selected perspectives once as one bounded self-review batch and report reduced independence |

Use the preferred tool only when it answers the current evidence question. Tool failure is not a domain finding: report reduced confidence and block only when missing evidence prevents a safe decision. Do not use semantic tooling for prose or configuration questions, and do not use web research to rediscover stable local facts.

Evidence Rules

| Evidence | Authority | |---|---| | Repository files, manifests, schemas, generated contracts, and executable behavior | Source of truth for the current project state | | Official vendor documentation, specifications, RFCs, and security standards | Source of truth for external contracts and current supported behavior | | Release notes and migration guides matching the project's actual version range | Source of truth for compatibility and upgrade claims | | Reputable primary engineering material | Supporting evidence when official sources do not address a design tradeoff | | Community discussion or training knowledge | Leads only; never sufficient for a blocking factual claim |

When sources disagree, prefer the repository for what is installed and implemented, and official documentation for what an external system promises. Repository evidence proves a plan defect; external practice sources justify the correction mechanism and cannot invent a local requirement. State disagreements instead of silently choosing the convenient answer.

Checklist

1. Establish the Review Contract

  • [ ] Resolve the exact plan, user request, linked requirements, and repository scope. If no concrete plan exists, stop with BLOCKED rather than inventing one to review.
  • [ ] Read all applicable repository instruction files before interpreting code, documentation, or expected workflow. Identify only change-relevant project policies, standards, and ADRs; distinguish current accepted authority from draft, superseded, stale, or merely descriptive material instead of treating every document as binding.
  • [ ] Inspect Git state when it can affect the review: current branch, uncommitted changes, comparison base, and relevant recent history.
  • [ ] Separate the literal request and proposed solution from the underlying intent; state the actor, protected outcome, observable definition of done, non-goals, constraints, and assumptions, and label unsupported intent inferences.
  • [ ] Calibrate acceptable complexity to evidenced project or product maturity, decision horizon, current scale, team and operational capacity, and business stakes. Treat future growth as a requirement only when a concrete horizon, consumer, load, or constraint supports it.
  • [ ] Separate defects in the plan from pre-existing adjacent problems. Treat an existing problem as a plan finding only when the plan introduces or worsens it, depends on a false assumption about it, must resolve it to satisfy the goal, or creates immediate delivery risk; otherwise record it as an out-of-scope observation and do not expand the plan.
  • [ ] Distinguish facts discoverable from the repository from choices that require user intent; explore first, and when plausible interpretations would produce materially different plans, ask one concise question that resolves the decision rather than a survey.
  • [ ] Classify the review depth. Treat authentication, authorization, money, destructive operations, data migration, public APIs, concurrency, distributed workflows, and irreversible rollout as high-risk.
  • [ ] Keep the run read-only. Do not mutate the source plan, implementation, task tracker, branch, or external system; a corrected plan may appear only in the review response. Allow only host-permitted rebuildable diagnostic caches or build artifacts and disclose them when created.

2. Ground the Plan in the Repository

  • [ ] Build a narrow map of the affected modules, entrypoints, configuration, schemas, migrations, tests, documentation, and deployment surfaces.
  • [ ] Discover shared architecture and governance artifacts by repository convention and common roles: system-design baseline, current-state map, target design, accepted decisions, engineering policies, diagrams, and migration plan. Treat them as optional evidence, never as required workflow dependencies.
  • [ ] Check artifact status, authority, owner, source, as-of date, supersession, and review triggers before applying a constraint. Keep one change-scoped policy and decision ledger of applicable sources and the plan evidence for compliance, explicit approved deviation, or an unresolved gap. Missing artifacts do not block review by themselves; a material unresolved driver does.
  • [ ] Verify every existing path, symbol, component, command, environment key, interface, and dependency named by the plan. Mark genuinely new artifacts as new.
  • [ ] Read enough implementation context to understand ownership and invariants, not just the files explicitly named by the plan.
  • [ ] Inspect Git history or blame only when it can reveal a still-relevant constraint or convention; do not treat historical code as proof that the current design is correct.
  • [ ] Check the existing test and CI surface so proposed verification commands, fixtures, environments, and acceptance evidence are feasible.
  • [ ] Keep an evidence ledger for material claims: claim, source, confidence, and the plan decision it supports or contradicts.
  • [ ] Check known concurrent work when it can collide with affected contracts, schemas, files, or outcomes; do not inventory every branch or plan without an overlap signal.
  • [ ] Stop expanding the scan when additional files cannot change a plan decision, finding, or confidence level.

3. Research Corrections and Unknown External Claims

  • [ ] Research a correction only after repository evidence establishes a material candidate gap; prefer an existing repository mechanism and do not browse to invent findings.
  • [ ] Extract plan claims that are external or unstable: versions, API signatures, deprecations, standards, security requirements, library capabilities, performance characteristics, and platform limits.
  • [ ] Resolve installed versions and enabled features from project manifests, lockfiles, configuration, and generated metadata before searching generic documentation.
  • [ ] Before recommending a correction that depends on an external API, library, security control, protocol, platform, standard, or version, verify the supported solution, constraints, deprecations, and security guidance in official documentation matched to the installed or proposed version.
  • [ ] For unresolved design tradeoffs, compare primary engineering evidence with local requirements and operating constraints; document where the evidence does not select a unique solution.
  • [ ] Open and inspect any specific document, proposal, issue, or URL that the plan relies on instead of trusting a quotation or paraphrase.
  • [ ] Add solution research to the material-claim ledger: source/date, suppo

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars566
CategoryLegal
Updated2mo ago
Forks84

Languages

PowerShell

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions