fix-finding
Skill2 starsChanged 47 days agoMITView on GitHub
Implements a verified-ready code or config fix for an owned finding in the Defense Factory Verified remediation phase. Use after ownership assignment; does not mark the finding verified—that requires verify-fix after deploy.
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Read finding + evidence + ownership SLA.
- Distinctive: line 27
Add or update automated tests that would fail on the old behavior when feasible.
- Distinctive: line 32
Test commands run locally
- Very specific: line 47
Do not claim verified_fixed from this skill.
- Distinctive: line 48
Do not “fix” by disabling tests or hiding scanner output without addressing the issue.
- Very specific: line 53
After deploy to the verification environment, run verify-fix.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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
fix-finding
Phase: Verified remediation (fix half)
Style: Blue (defensive)
When to use
- Validated finding has an ownership assignment
- User asks to remediate a specific finding id
Preconditions
- Finding status is
validatedorremediating. - Ownership assignment exists under
.defense-factory/ownership/. - Authorization to modify the target repository.
- Clear reproduction notes from validation (so the fix addresses the proven issue).
Procedure
- Read finding + evidence + ownership SLA.
- Implement the minimal fix (code, config, dependency bump, or feature flag) that addresses root cause.
- Add or update automated tests that would fail on the old behavior when feasible.
- Open a PR or commit per project norms; record references in
.defense-factory/remediation/<finding-id>.md:- Finding id
- Change summary
- PR URL / commit SHAs
- Test commands run locally
- Residual risk
- Set finding
statustofixed_pending_verify(notverified_fixed). - Explicitly note in the remediation doc: merged PR is not remediation complete.
Required outputs
| Path | Notes |
| Code/config changes in the target repo | Actual fix |
.defense-factory/remediation/<finding-id>.md | Remediation record |
| Updated finding JSON | fixed_pending_verify |
Stop / refuse
- Do not claim
verified_fixedfrom this skill. - Do not “fix” by disabling tests or hiding scanner output without addressing the issue.
- Refuse fixes that intentionally weaken security controls without documented risk acceptance in SECURITY.md.
Next phase
After deploy to the verification environment, run verify-fix.
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- openai/codex-security★ 11ksame name
- openai/plugins★ 7.4ksame name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- build-inventorySkill
- dedupe-findingsSkill
- define-security-policySkill
- 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
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.