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 tomzx/agents --skill identify-bugsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/identify-bugs)<a href="https://agentmods.dev/skills/tomzx/agents/identify-bugs"><img src="https://agentmods.dev/badge/skills/tomzx/agents/identify-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/tomzx/agents/identify-bugs"><img src="https://agentmods.dev/badge/skills/tomzx/agents/identify-bugs.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 | $0.00140 | $0.05155 |
| Opus 5.5 | $0.00056 | $0.02062 |
| Sonnet 5.5 | $0.00028 | $0.01031 |
| Haiku 4.5 | $0.00014 | $0.00515 |
Grade A, and why
identify-bugs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d REPO=!git remote get-url origin 2>/dev/null | sed -E 's#.*[:/]([^/]+/[^/]+)(\.git)?$#\1#'
Identify Bugs
Reads an existing codebase and surfaces latent defects that are worth fixing and are not already tracked in the issue tracker.
Every candidate must clear three gates: high confidence (the code path exists and is reachable), verification where possible (a failing test or runnable repro), and not already an existing GitHub issue.
The dedup is what keeps the pass useful: the skill loads the issue history with ghx up front and re-checks each candidate, dropping anything tracked and continuing until no untracked bug remains.
This is a proactive, whole-codebase hunt. It does not modify or commit source code. It produces a ranked bug report, and optionally files issues for the bugs that survive dedup.
The Core Problem This Solves
Bugs are usually found by accident, from a stack trace or a user report. A static scan in the other direction produces a pile of "probably a bug" claims, most of which are handled elsewhere, are by design, or are already known. Both directions waste effort. This skill reads the code deliberately, states the exact input and state that produces wrong behavior, verifies the claim where a test seam exists, and excludes anything already tracked, so what it reports is worth acting on.
How This Differs From Related Skills
| Skill | Direction | Input | Output |
|---|---|---|---|
identify-bugs |
Proactive hunt for unknown defects | Whole codebase | Ranked, verified, untracked bugs |
reproduce-issue |
Confirm one known bug | A GitHub issue | A reproduction comment |
diagnosing-bugs / systematic-debugging |
Diagnose one known symptom | A failure | A root cause |
review-pr / identify-style diff review |
Bugs introduced by a change | A diff | Review findings |
audit-functional-suitability |
Does the code meet requirements | Requirements corpus | Completeness and correctness signals |
identify-codebase-improvements |
Make correct code better | Whole codebase | Improvement recommendations |
audit-security |
Security vulnerabilities | Whole codebase | Security findings |
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.
- 16d ago Changed · +38 lines 7fd12f789c4c
- 22d ago Changed · +28 lines 839efc40e3ad
- 25d ago Changed e511053c879e
- 27d ago First seen · 332 lines · 140 tokens per session scan A ce2023bcf232
identify-bugs is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 5,155 once invoked, about $0.0006 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 2026-10-03.
Other skills, from other repositories
sync-bridge
Reviews and guides Chromium Sync Model API (DataTypeSyncBridge) implementations, including DataTypeStore persistence and forwards/backwards compatibility for sync specifics. Use when implementing or reviewing a DataTypeSyncBridge subclass, DataTypeStore usage, sync metadata persistence, conflict resolution, or…
sync-model-processor
Reviews changes to Chromium Sync model internals in components/sync/model/, including ClientTagBasedDataTypeProcessor, ClientTagBasedRemoteUpdateHandler, ProcessorEntity, ProcessorEntityMetadata, and ProcessorEntityTracker. Use when modifying or reviewing processor state transitions, entity metadata tracking, conflict…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
gsd-ns-review
Invoke this Pi skill with /skill:gsd-ns-review.
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…