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 tsai09495/matt-pocock-engineering --skill diagnosing-bugsgit clone --depth 1 https://github.com/tsai09495/matt-pocock-engineeringWrote 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/tsai09495/matt-pocock-engineering/diagnosing-bugs)<a href="https://agentmods.dev/skills/tsai09495/matt-pocock-engineering/diagnosing-bugs"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/diagnosing-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/tsai09495/matt-pocock-engineering/diagnosing-bugs"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/diagnosing-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 | $0.00051 | $0.02203 |
| Opus 5 | $0.00026 | $0.01102 |
| Sonnet 5 | $0.00010 | $0.00441 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
diagnosing-bugs scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Phase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** — a script path, a test invocation, a curl — that you have **already run at least once** (show the invocation and its redacted How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnosing Bugs
A discipline for hard bugs. Skip phases only when explicitly justified.
Read quality-baseline.md before claiming completion.
When exploring the codebase, read CONTEXT.md (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
Redact sensitive evidence
This workflow shows commands, outputs, logs, traces, and captured artifacts. Redact secrets, tokens, cookies, authorization headers, credentials, and personal data before displaying or preserving them. Replace each removed value with <REDACTED> (as inert code text) so the evidence structure remains visible.
Build feedback loops against environment variables or an approved secret store; do not place credential values in scripts, command examples, transcripts, durable notes, or test records. Quote only the smallest lines that carry the diagnostic signal. A HAR, log dump, core dump, or screen capture may contain sensitive data even when the visible symptom does not.
If redacted evidence is insufficient, say what signal is missing and ask the user for a safer access or capture method. Do not request that a secret be pasted into the conversation.
Phase 1 — Build a feedback loop
This is the skill. Everything else is mechanical. If you have a tight pass/fail signal for the bug — one that goes red on this bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.
Spend disproportionate effort here. Be aggressive. Be creative. Refuse to give up.
Ways to construct one — try them in roughly this order
- Failing test at whatever seam reaches the bug — unit, integration, e2e.
- Curl / HTTP script against a running dev server.
- CLI invocation with a fixture input, diffing stdout against a known-good snapshot.
- Headless browser script (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
- Replay a captured trace. Save a real network request / payload / event log to disk; replay it through the code path in isolation.
- Throwaway harness. Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
- Property / fuzz loop. If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
- Bisection harness. If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can
git bisect runit. - Differential loop. Run the same input through old-version vs new-version (or two configs) and diff outputs.
- HITL bash script. Last resort. If a human must click, drive them with
scripts/hitl-loop.template.shso the loop is still structured. Captured output feeds back to you.
What ships with it
2 files 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.
- 9d ago First seen · 145 lines · 51 tokens per session scan A d12a1730b956
diagnosing-bugs is a skill published in the GitHub repository tsai09495/matt-pocock-engineering (2 stars, last pushed 14d ago), licensed MIT. It adds 51 tokens to every session and 2,203 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
postmortem
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
bug-localization
Identify the precise location of bugs in source code, modules, and systems. Use this skill when debugging applications, investigating test failures, analyzing error reports, tracing runtime issues, or performing root cause analysis. Analyzes stack traces, error messages, failing tests, and code patterns to pinpoint…
bug-to-patch-generator
Generate code fixes and patches from bug reports, failing test cases, error messages, and stack traces. Use this skill when debugging code, fixing test failures, addressing GitHub issues, resolving runtime errors, or patching security vulnerabilities. Analyzes the bug context, identifies root causes, and generates…
counterexample-generator
Generate concrete counterexamples when formal verification, assertions, or specifications fail. Use this skill when debugging failed proofs, understanding why verification fails, creating minimal reproducing examples, analyzing assertion violations, investigating invariant breaks, or diagnosing specification…
error-explanation-generator
Explains test failures and provides actionable debugging guidance. Use when tests fail (unit, integration, E2E), builds fail, or code throws errors. Analyzes error messages, stack traces, and test output to identify root causes and suggest concrete fixes. Handles pytest, jest, junit, mocha, vitest, selenium, cypress…