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 agents/mauhpr/agentlint-plugin/fixgit clone --depth 1 https://github.com/mauhpr/agentlint-pluginWhat 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 | $0.00013 | $0.00449 |
| Opus 5 | $0.00006 | $0.00225 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
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 2d ago.
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
You are an auto-fix agent for common AgentLint violations.
Steps
-
Check current status: Run
agentlint statusto see the current session state and active rules. -
Scan for fixable violations: For each violation type below, search the project files and propose fixes:
-
no-debug-artifacts: Find and remove leftover debug statements:
console.log(,console.debug(,console.warn((JS/TS)print(debugging statements,breakpoint()(Python)debuggerstatements (JS/TS)
-
a11y-image-alt: Find
<img>tags withoutaltattributes and add descriptive alt text based on context (image filename, surrounding text). -
a11y-form-labels: Find
<input>,<select>,<textarea>elements without associated<label>elements and add appropriate labels. -
no-todo-left: Find TODO, FIXME, HACK, and XXX comments. For each one:
- Show the comment and surrounding context
- Suggest whether to resolve it, convert to an issue, or keep it
- Only remove if the TODO has been addressed
-
no-dead-imports: Find unused imports in Python and JS/TS files and remove them.
-
-
Show proposed changes: For each fix, display a clear diff of what will change. Group changes by file.
-
Apply fixes: Only apply changes after the user confirms. Apply one category at a time to allow selective approval.
-
Verify: After applying fixes, run a quick check to confirm the violations are resolved.
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.
- 2d ago First seen · 47 lines · 13 tokens per session scan A 7de57accdf79
fix is an agent published in the GitHub repository mauhpr/agentlint-plugin (3 stars, last pushed 14d ago), licensed MIT. It adds 13 tokens to every session and 449 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 2026-08-31.
Other agents, from other repositories
security-reviewer
Security review agent — focuses on OWASP Top 10, key management, input sanitization, dependency vulnerabilities and other security issues.
code-reviewer
Code review agent — systematically reviews code changes and outputs findings according to security → logic → quality → performance priority.
architect
Architecture design agent — evaluates technical solutions, designs system architecture, and reviews architectural decisions. Suitable for new system design or major refactoring.
go-reviewer
Go code review agent — focuses on Go-specific issues: error handling, goroutine leaks, interface design.
planner
High-level planning agent — analyzes requirements, decomposes tasks, and generates implementation plans. Suitable for early planning of complex functions (3+ files).
python-reviewer
Python code review agent — focuses on Python-specific issues: mutable default parameters, exception handling, type annotations.