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 agentmods add skills/danielvm-git/bigpowers/investigate-bugnpx skills add danielvm-git/bigpowers --skill investigate-buggit clone --depth 1 https://github.com/danielvm-git/bigpowersWhat 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 | $0.00064 | $0.01252 |
| Opus 5 | $0.00032 | $0.00626 |
| Sonnet 5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
investigate-bug 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate Bug
Boundary: End-to-end bug entry point — history check → RCA (via diagnose-root) → fix approach → TDD plan → bug file. Delegates the 4-phase RCA to diagnose-root; does not re-implement it.
Investigate a reported problem, find its root cause, and write a TDD fix plan to specs/bugs/BUG-*.md. This is a mostly hands-off workflow — minimize questions to the user.
Process
0. Read previous bug history
Before starting diagnosis:
- Read
specs/bugs/registry.yaml(if it exists) — check for prior bugs in the samescopeor with similar symptoms. - If a relevant prior bug is found, read the corresponding
specs/bugs/BUG-*.mdfile to understand previous root cause analysis and fix approach. - Note in your investigation whether this is a recurrence, a related issue, or novel.
1. Capture the problem
Get a brief description of the issue from the user. If they haven't provided one, ask ONE question: "What's the problem you're seeing?"
Do NOT ask follow-up questions yet. Start investigating immediately.
Security-impact assessment — After capturing the problem, assess and document:
Security impact: NONE / LOW / MEDIUM / HIGH / CRITICAL. If HIGH or CRITICAL, assign bug severity HIGH and document the exploit path in findings. If MEDIUM+, include exploit path in the bug file. Document "no security exploit path identified" for NONE/LOW.
2. Explore and diagnose (4-phase RCA)
Run the 4-phase root-cause analysis via the diagnose-root skill (Reproduce → Isolate → Hypothesize → Verify). That skill is the canonical RCA engine — do not re-implement the phases here.
Also look at:
- Recent changes to affected files (
git log --oneline <file>) - Existing tests (what's tested, what's missing)
- Similar patterns elsewhere in the codebase that work correctly
HARD GATE — Do NOT proceed to Step 3 (Fix Approach) until
diagnose-rootPhase 4 produces a verified root cause. "It probably is X" is not verified.
3. Identify the fix approach
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.
- 2d ago First seen · 128 lines · 64 tokens per session scan A 5354cd9022a8
investigate-bug is a skill published in the GitHub repository danielvm-git/bigpowers (156 stars, last pushed 26d ago), licensed MIT. It adds 64 tokens to every session and 1,252 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 2026-08-30.
Other skills, from other repositories
pm/competitive-analysis
竞品调研和分析方法，通过系统性分析竞品的功能、体验和策略，发现差异化机会.
macrothink
User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without treating convergence as proof.
nba
Read the live cycle state and return the single highest-leverage next best action, not a menu. Use when a project is between phases, the author asks what to do next, too many valid threads are open, or the work needs re-entry into frame, build, drive, re0-memo, hate, re0-work, or ship.
bmad-dev-story
Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan".
bmad-domain-research
Conduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]".
harness-engineering
Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.