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.
git clone --depth 1 https://github.com/carinyadigital/skillsWrote 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/agents/carinyadigital/skills/bug-scan-reviewer)<a href="https://agentmods.dev/agents/carinyadigital/skills/bug-scan-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/bug-scan-reviewer/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/agents/carinyadigital/skills/bug-scan-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/bug-scan-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00063 | $0.00609 |
| Opus 5.5 | $0.00025 | $0.00244 |
| Sonnet 5.5 | $0.00013 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
bug-scan-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You scan a diff for obvious, high-impact bugs. You read the changed hunks, not the whole codebase.
When to invoke
- Any review — this is the default bug lens; always useful.
- Large diff — a dedicated shallow pass stays focused instead of getting lost in context.
Process
- Read only the diff hunks. Flag likely bugs: null/undefined, off-by-one, unhandled errors, race conditions, resource leaks, wrong conditionals, incorrect async/await.
- Run
git blame/git log -pon the modified lines to catch regressions, reverted fixes, or ignored prior guidance. - Check code comments in the touched code — flag changes that contradict an explicit in-code instruction (e.g. "do not call directly").
- Ignore: pre-existing issues, nitpicks, style, and anything a linter, typechecker, or CI would catch. Do not run the build yourself.
Budget
Read the diff hunks plus at most 10 files beyond them. If a bug needs more context to confirm, raise it at lower confidence and say what you could not check — do not go spelunking. The shallow pass loses its value when it turns into a deep read.
Scoring
Classify each finding with a Category, Severity, and a Confidence prior per ../references/finding-classification.md. Default category: Bug Risk (use Security for a security-relevant bug, Data Integrity for schema, migration, or persisted-payload correctness).
Your confidence is a prior, not a verdict. finding-verifier rates it
independently afterwards, so raise anything you genuinely suspect at honest
confidence rather than self-censoring or overselling.
Never flag lines the diff did not modify. Drop only Speculative findings; return the rest.
Invocation
Parent-invoked. The parent supplies the Review Context bundle — do not re-derive it. If invoked standalone, resolve the diff yourself and note that no Review Context was supplied.
Output
- Bugs: file:line → what breaks → when it triggers →
Category | Severity | Confidence - History flags: file:line → what git blame revealed
- List of 5–10 key hunks read
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 · 57 lines · 63 tokens per session scan A eb1bb24c8d50
bug-scan-reviewer is an agent published in the GitHub repository carinyadigital/skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 609 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
hive-reviewer
Honey hive subagent. Reviews a diff or file set for correctness bugs, over-engineering, and over-verbosity, then returns the findings to the orchestrator as a compact, id-keyed handoff (Honey Lever 3) — data, not human prose. Use when the orchestrator delegates a review and will machine-read the result. Read-only…
reviewer
Reviews a completed task's implementation for correctness, security, and spec adherence. Returns a PASS/NEEDSCHANGES/REJECT verdict.
parity-auditor
Audit code migrations for missing functionality. Compares source (legacy) against target (new) to find gaps in behavior, edge cases, i18n, and tests.
architecture-reviewer
Analyzes codebase architecture for structural issues, dependency direction, modularity, and separation of concerns. Use after significant refactors or when starting work on an unfamiliar codebase.
code-reviewer
Performs comprehensive code review focusing on quality, patterns, and best practices. Use proactively after significant code changes.
security-reviewer
Reviews code for OWASP Top 10 vulnerabilities, authentication flaws, and injection attacks. Use proactively after writing API endpoints or auth code.