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 skills add minghinmatthewlam/agent-guards --skill find-bugsgit clone --depth 1 https://github.com/minghinmatthewlam/agent-guardsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/minghinmatthewlam/agent-guards/find-bugs)<a href="https://agentmods.dev/skills/minghinmatthewlam/agent-guards/find-bugs"><img src="https://agentmods.dev/badge/skills/minghinmatthewlam/agent-guards/find-bugs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/minghinmatthewlam/agent-guards/find-bugs"><img src="https://agentmods.dev/badge/skills/minghinmatthewlam/agent-guards/find-bugs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00048 | $0.00403 |
| Opus 5.5 | $0.00019 | $0.00161 |
| Sonnet 5.5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
find-bugs 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 1mo 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
Find Bugs
Understand the real behavior before judging it. Trace relevant entrypoints, callers, tests, state transitions, invariants, and failure paths.
Investigate
- Prioritize high-confidence, high-impact findings. When impact and confidence are similar, favor lower-complexity fixes, but do not hide a severe bug because its fix is complex.
- Explore adaptively. Use subagents when they materially improve coverage, keep their scopes distinct, and consolidate their findings centrally.
- Verify consequential findings with a focused reproduction, test, or runtime probe when practical.
- Remain read-only unless the user asks for fixes.
Report Findings
For each material finding:
- put priority, expected fix complexity, finding confidence percentage, and fix
confidence percentage in the heading so they are immediately scannable, for
example
P1 — [Medium fix, 98% finding confidence, 90% fix confidence] Cache entries are not isolated; - state the proposed fix direction that the fix estimates refer to;
- state the expected impact of the fix and explain material risk, blast radius, trade-offs, or unknowns behind the fix confidence.
Include enough of the following to substantiate it:
- affected files and symbols;
- trigger or edge case;
- expected versus actual behavior;
- user or system impact;
- concrete code, test, or runtime evidence;
Keep simple findings compact; omit fields that do not add clarity.
Only call something a bug when the execution path and expected contract support that conclusion. Separate verified bugs from plausible investigation leads. Do not report style preferences, intentional trade-offs, or unrealistic edge cases as correctness bugs.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 48 lines · 48 tokens per session scan A 037f363d1ed5
find-bugs is a skill published in the GitHub repository minghinmatthewlam/agent-guards (47 stars, last pushed 8d ago), licensed MIT. It adds 48 tokens to every session and 403 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…