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 toverux/cantrips --skill diagnosing-bugsgit clone --depth 1 https://github.com/toverux/cantripsWrote 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/toverux/cantrips/diagnosing-bugs)<a href="https://agentmods.dev/skills/toverux/cantrips/diagnosing-bugs"><img src="https://agentmods.dev/badge/skills/toverux/cantrips/diagnosing-bugs.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.02399 |
| Opus 5 | $0.00020 | $0.01200 |
| Sonnet 5 | $0.00008 | $0.00480 |
| Haiku 4.5 | $0.00004 | $0.00240 |
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 3d 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 output, r How it starts
The opening of the file, as written. The whole thing — 150 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.
Phase 0 — Search past learnings and decisions
When the loop config enables the solutions store, search docs/solutions/ for learnings matching the symptom — the error message, the module, the failure mode.
When it enables the ADR store, read the ADRs bearing on the area you are touching, so the fix you design does not re-litigate a decision already made.
The loop config is docs/agents/cantrips-loop.md; when that doc is absent, both stores are off.
A past solution may short-circuit the whole diagnosis: when one matches, verify its root cause applies here before building anything, and carry its gotchas into the phases below.
Redact
This skill has you show commands, outputs and captured artifacts. Redact every secret first — write <REDACTED> in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal.
If the redacted output is not enough to diagnose the bug, say so and ask the user.
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.
- 3d ago Changed · +6 lines a48b60006628
- 8d ago First seen · 144 lines · 40 tokens per session scan A cb6bbddd82aa
diagnosing-bugs is a skill published in the GitHub repository toverux/cantrips (2 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 2,399 once invoked, about $0.0002 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
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.
checking-code-quality
Checks code quality metrics including complexity, duplication, naming conventions, and function length. Use when running quality gates, reviewing code smells, or checking lint rules. Automatically triggered on complex modules or post-refactor.
find-bugs
Locate likely bug locations in code.
code-review
Perform comprehensive code reviews covering bugs, style, performance, security, and best practices. Use this skill when the user mentions: review my code, check this code, code review, find bugs, improve code, refactor suggestions, security audit, performance optimization, code quality, static analysis.
causal-explanation
Explain why or how an existing consequential behavior, design choice, regression, threshold, or tradeoff exists from current evidence and relevant history. Use for why, how, rationale, or postmortem questions and to explain an established root cause or regression finding; do not use to reproduce, diagnose, or…