kenhuanguskenhuangus/defense-factory-skills/AGENTS.md

defense-factory-skills

AGENTS.md2 starsChanged 47 days agoMITView on GitHub

These skills are Ken Huang illustrative Defense Factory skills, not official OpenAI Codex Security skills. Use them only for authorized defensive security work. Skip forward only when prior-phase artifacts already exist and are valid. Stop and refuse when asked to:

We split this AGENTS.md into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Read repo-root SECURITY.md or .defense-factory/SECURITY.md.
line 8
Very specific:
Prefer Blue/defensive procedures.
line 9
Very specific:
Write artifacts under .defense-factory/ using the schemas in schemas/.
line 10
Very specific:
Run python scripts/validate_artifacts.py <artifact.json> before treating an artifact as complete.
line 11
Distinctive:
Stop and refuse when asked to:
line 28
Distinctive:
Use concrete paths, commands, and evidence file references.
line 37
Distinctive:
Keep prose technical; avoid metaphors in security reports.
line 39

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

Agent instructions — defense-factory-skills

These skills are Ken Huang illustrative Defense Factory skills, not official OpenAI Codex Security skills. Use them only for authorized defensive security work.

Before any skill

Confirm the user owns the target or has written authorization to test it.
Read repo-root SECURITY.md or .defense-factory/SECURITY.md. If missing, run define-security-policy first (or scripts/init_workspace.py).
Prefer Blue/defensive procedures. Use Red-style reproduction only inside triage-validate-finding when authorization is explicit.
Write artifacts under .defense-factory/ using the schemas in schemas/.
Run python scripts/validate_artifacts.py <artifact.json> before treating an artifact as complete.

Phase order

define-security-policy → threat-model
        → build-inventory
        → security-scan / security-diff-scan
        → triage-validate-finding → dedupe-findings
        → route-ownership
        → fix-finding → verify-fix

Skip forward only when prior-phase artifacts already exist and are valid.

Refusal

Stop and refuse when asked to:

Build or refine exploits against unauthorized third-party systems
Mark findings validated from static results alone
Close remediation solely because a PR merged
Bypass disclosure or authorization gates in SECURITY.md

Output quality

Use concrete paths, commands, and evidence file references.
Redact secrets in saved proof artifacts.
Keep prose technical; avoid metaphors in security reports.

Download now (ZIP)

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 28,693 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 repository10 other files it gives its agents.
- build-inventorySkill
- dedupe-findingsSkill
- define-security-policySkill
- fix-findingSkill
- route-ownershipSkill
- security-diff-scanSkill
- security-scanSkill
- threat-modelSkill
- triage-validate-findingSkill
- verify-fixSkill

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free