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 atman-33/workhub --skill investigate-bug-reportgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/investigate-bug-report)<a href="https://agentmods.dev/skills/atman-33/workhub/investigate-bug-report"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/investigate-bug-report/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/atman-33/workhub/investigate-bug-report"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/investigate-bug-report.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 | $0.00070 | $0.00701 |
| Opus 5 | $0.00035 | $0.00351 |
| Sonnet 5 | $0.00014 | $0.00140 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
investigate-bug-report 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 9d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate Bug Report
Diagnose, don't fix. The deliverable is a root-cause finding with evidence — apply a fix only if the user then asks.
Steps
-
Pin down the report. Extract from the report (ask only for what's missing and blocking): observed behavior, expected behavior, steps or input that trigger it, environment/version if relevant.
- Completion criterion: you can state "given X, it does Y, but should do Z" in one sentence.
-
Reproduce — or trace when you can't. Prefer an actual reproduction (run the failing command, a minimal script, or an existing test tightened to the case). When reproduction isn't feasible (needs external services, prod-only data), trace the code path statically from the entry point the report implies, and say the diagnosis is trace-based.
- Completion criterion: the failure is observed firsthand, or the full
path from trigger to symptom is traced with
file:linehops.
- Completion criterion: the failure is observed firsthand, or the full
path from trigger to symptom is traced with
-
Isolate the root cause. Follow the data from symptom back to the first point where state or logic diverges from intent. Distinguish the root cause from where the error surfaces — they are usually different lines. Check
git log/git blameon the suspect code: a recent change that introduced it is strong corroborating evidence.- Completion criterion: one specific location (
file:line) and mechanism explains every symptom in the report. A cause that explains only some symptoms is a co-incident finding, not the root cause — keep digging or report the gap explicitly.
- Completion criterion: one specific location (
-
Assess blast radius. Find other callers/inputs that hit the same defect (Grep for the pattern, referencing symbols). Note data that may already be corrupted if the bug writes state.
- Completion criterion: every caller of the defective code is classified affected / unaffected.
-
Propose fix candidates. 1–3 options with tradeoffs (minimal patch vs. proper restructure), the recommended one first, plus the regression test that would have caught this.
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.
- 9d ago First seen · 62 lines · 70 tokens per session scan A b78864b9cc1d
investigate-bug-report is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 701 once invoked, about $0.0003 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 skills, from other repositories
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
stress-test
Use when a design, plan, or decision needs adversarial scrutiny before proceeding. Interrogates every branch of the decision tree, providing recommended answers and forcing explicit agreement or pushback. Triggers on "grill me", "stress test this", "poke holes", "challenge this design", or when…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-fix
A bug-fixing skill with separate paths for directly reported bugs, correctness-review findings, and failed verification or quality-gate reports. It records completed fixes and their validation in project reports.