Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/matteocervelli/llms/issue-fixgit clone --depth 1 https://github.com/matteocervelli/llmsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.00538 |
| Opus 5 | $0.00007 | $0.00269 |
| Sonnet 5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
issue-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Fix Bug from Issue: $ARGUMENTS
💡 Tip: For safer planning, activate Plan Mode (press Shift+Tab twice) before running this command to review the fix strategy before implementation.
Analysis Phase
!gh issue view $ARGUMENTS
!git checkout -b fix/issue-$ARGUMENTS
Use sequential-thinking-mcp to:
- Understand the bug and identify root cause
- Assess security implications (auth, input validation, data exposure)
- Plan minimal fix with performance considerations
- Identify testing strategy
Implementation Phase
Implement fix following:
- Security: Validate inputs, secure error handling, no data leaks
- Performance: Measure impact, optimize queries if needed
- Defensive: Null checks, proper error boundaries
Testing Phase
# Quality checks
!npm run lint && npm run typecheck || flake8 . && mypy .
!npm run test || pytest
Create tests for:
- Bug reproduction (verify fix works)
- Security edge cases (malicious inputs)
- Performance regression (response times)
- Integration scenarios
Validation Checkpoint
Test the fix in development and confirm:
- Original bug is resolved
- No regressions in existing functionality
- Performance impact acceptable
- Security measures working
Deploy Phase
!git add . && git commit -m "fix: resolve issue $ARGUMENTS
- Root cause: [brief description]
- Security: [input validation/auth preserved/no data exposure]
- Performance: [within SLA/optimized/no regression]
- Testing: [unit/integration/security tests added]
Fixes #$ARGUMENTS"
!git push origin fix/issue-$ARGUMENTS
!gh pr create --title "fix: issue $ARGUMENTS" --body "Security-validated bug fix with performance testing. Fixes #$ARGUMENTS"
Documentation
Update:
docs/implementation/with fix detailsdocs/developers/TROUBLESHOOTING.mdif neededdocs/architecture/docs if structural changesdocs/guides/docs if user guide changes
Final Steps
- Update @CHANGELOG.md with bug fix addition and increase versioning accordingly
- Update user documentation and publish if needed
- Monitor bug fix adoption and performance post-deployment
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 86 lines · 14 tokens per session scan A c115cd9a2487
issue-fix is a command published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 538 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.