codex-factory / i-test-target
AGENTS.md100 starsChanged 59 days agoMITView on GitHub
These rules apply to all Codex sessions within this Harness repository. Detailed documentation: docs/harness-rules.md, docs/harness-runbook.md, docs/harness-audit-contract.md
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- harness/AGENTS.mdAGENTS.md
- anti-overengineeringSkill
- app-type-classifierSkill
- auth-permission-securitySkill
- backend-api-designSkill
- CAP-SKILL-004Skill
- CAP-SKILL-013Skill
- CAP-SKILL-014Skill
- CAP-SKILL-015Skill
- database-schema-designSkill
- frontend-ui-systemSkill
- mobile-miniapp-patternsSkill
- product-architectureSkill
- webapp-preview-testingSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
No direct canonical modification: Never modify app source directly.
- Distinctive: line 10
Task binding required: Every modification must bind to a taskId, allowedPaths, and baseCanonicalHash.
- Distinctive: line 11
Evidence completeness: Every command must capture stdout, stderr, and exitCode.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Harness Safety Invariants (AGENTS.md)
These rules apply to all Codex sessions within this Harness repository. Detailed documentation: docs/harness-rules.md, docs/harness-runbook.md, docs/harness-audit-contract.md
Hard Constraints
- No direct canonical modification: Never modify app source directly. All changes must go through allowed task workspace paths + integration.
- Builder cannot self-verify: Verification must use an independent test-agent role with separate token.
- Task binding required: Every modification must bind to a taskId, allowedPaths, and baseCanonicalHash.
- Evidence completeness: Every command must capture stdout, stderr, and exitCode.
- validate-state ≠ engineering PASS: validate-state.ps1 checks governance; engineering verification checks functionality. Both must pass.
- No capability inflation: Reports must not claim untested capabilities as proven.
- Sidecar meta: Final ZIP digest must be recorded in external .meta.json, never inside the ZIP.
- Cognitive isolation: Strong cognitive isolation is NOT PROVEN. OS-level isolation is NOT PROVIDED.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.