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/jnarowski/agentcmd/fixgit clone --depth 1 https://github.com/jnarowski/agentcmdWhat 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 | $0.00011 | $0.00502 |
| Opus 5 | $0.00005 | $0.00251 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix
Runs all validation commands found in readme, and automatically fixes all issues including warnings. Iterates until validation passes with no errors or warnings.
Workflow
-
exceute "pnpm check" - this runs check-types, lint and test
-
Run Initial Validation
- Execute the validation command using the Bash tool
- Capture the full output including errors, warnings, and info messages
- Parse the output to identify all issues that need fixing
-
Create Fix Plan
- Use TodoWrite to create a todo list with all issues found
- Group similar issues together (e.g., "Fix 5 type errors", "Fix 3 lint warnings")
- Mark the first issue as in_progress
-
Fix Issues Automatically
- Fix all issues without prompting for confirmation, even if they aren't related to code you wrote
- For each issue or group of issues:
- Analyze the root cause
- Apply the fix using appropriate tools (Edit, Write, Bash)
- Mark the todo as completed
- Mark the next todo as in_progress
- Common fix patterns:
- Type errors: Add type annotations, fix incorrect types, update interfaces. For TypeScript issues that cannot be fixed, use
@ts-ignorecomments only as a last resort - Lint warnings: Format code, remove unused imports, fix style issues
- Test failures: Update test expectations, fix broken logic, mock missing dependencies
- Build errors: Fix import paths, resolve missing dependencies, update configs
- Type errors: Add type annotations, fix incorrect types, update interfaces. For TypeScript issues that cannot be fixed, use
-
Verify Fixes
- Re-run the validation command
- Check if all issues are resolved
- If new issues appeared, add them to the todo list and continue fixing
- Repeat until validation command exits with success (exit code 0)
-
Report Results
- Report the total number of issues fixed
- Show the final validation output
- List any remaining issues that could not be auto-fixed (if any)
Report
After completion, report:
- The validation command that was executed
- Number of issues found initially
- Summary of fixes applied (grouped by category)
- Final validation status (pass/fail)
- Full output of the final validation run
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 · 56 lines · 11 tokens per session scan A 594457cf1dd9
fix is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 502 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.