harness
Field note and 70-second film contrasting one-shot model answers with an agent harness, plus askcline, a Bash wrapper for the Cline CLI.
Install / Use
npx skills add zozo123/free-intelligenceInstalls into whichever agent you are using.
Our assessment of harness
harness scores 44/100 on our quality scale, 209th of 216 Legal skills we index.
Its .clinerules is 2.3 KB long, lightly structured (2 headings) and no code examples: moderately detailed.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- Our last check on 2026-10-18 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur 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 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
harness compared with similar skills
All 4 of these similar skills score higher than harness; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| harness (this skill)by zozo123 | 44 | 0 | — | .clinerules |
| ui-ux-pro-maxby nextlevelbuilder | 100 | 143.4k | 5d ago | SKILL.md |
| constraint-driven-developmentby addyosmani | 100 | 112.2k | 5d ago | SKILL.md |
| ccs-alignby thedotmack | 100 | 107.6k | 5d ago | SKILL.md |
| design-isby thedotmack | 100 | 107.6k | 5d ago | SKILL.md |
Frequently asked questions
- How do I install harness?
- Run
npx skills add zozo123/free-intelligence. The install tabs above show the steps for each supported agent. - Which AI agents does harness work with?
- It is written for Cline, as a .clinerules file. Other agents that read the same format can often use it too.
- Is harness 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 declares no license and scores 68/100 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 harness still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubRepository operating contract
askcline "task" is the product: one command into Cline's full end-to-end agent harness.
- Every user-facing mode must dispatch to the official Cline CLI. Do not add or restore a direct Chat Completions HTTP client.
- A plain task must inspect, implement, validate, diagnose failures, retry, review the diff, and summarize the finished state.
rawis only a deprecated compatibility alias for the harness-backedtextmode.- Delegate authentication, provider/model configuration, streaming, sessions, tools, and context management to Cline.
- Never read or parse private Cline session credentials and never collect credentials in the static site.
- Agent mode defaults to autonomous execution, high reasoning, multiple retries, and no artificial timeout. Keep a narrow catastrophic-command deny policy and make safer overrides explicit.
- Never claim tests, lint, type checks, builds, citations, or rendered media passed unless they were actually produced and inspected.
- Preserve unrelated user changes and avoid expanding scope silently.
- Verification mode must disambiguate entities, inspect evidence, cite inspected sources, distinguish inference, and abstain when evidence is insufficient.
- Every behavior change to
public/askclinerequires deterministic tests proving all modes still invokecline.
Story and media contract
- The public thesis is: models propose, harnesses act, evidence decides, humans remain accountable.
- Keep the historical one-shot receipts clearly separate from the current harness implementation.
- State that the exact historical model configuration was not preserved; call the receipts demonstrations, not a reproducible benchmark.
- Never imply that a harness guarantees correctness, that auto-approved execution is sandboxed, or that every model run costs $0.
- The wrapper is free; provider and model charges may vary.
- Keep
index.html,README.md, the Remotion source, poster, OG card, and rendered film narratively consistent. - Rendered media must be generated from
free-intelligence-film/src/Composition.tsx, validated in CI, and accompanied bypublic/media-manifest.json. - Do not require byte-identical lossy MP4 encodes. Verify stable movie properties and compare deterministic Remotion still checkpoints from the actual timeline byte-for-byte.
Related Skills
ui-ux-pro-max
143.4kUI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation.
constraint-driven-development
112.2kEstablishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-i…
ccs-align
107.6kRun the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → get_observations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk hous…
design-is
107.6kAudit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
