Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/danielvm-git/bigpowersnpx agentmods add skills/danielvm-git/bigpowers/validate-fixWrote 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/danielvm-git/bigpowers/validate-fix)<a href="https://agentmods.dev/skills/danielvm-git/bigpowers/validate-fix"><img src="https://agentmods.dev/badge/skills/danielvm-git/bigpowers/validate-fix/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/danielvm-git/bigpowers/validate-fix"><img src="https://agentmods.dev/badge/skills/danielvm-git/bigpowers/validate-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 3 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Agent Snooping · line 113 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 146 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00056 | $0.01351 |
| Opus 5.5 | $0.00022 | $0.00540 |
| Sonnet 5.5 | $0.00011 | $0.00270 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
validate-fix 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 1mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Fix
HARD GATE — Fix must not regress. Run full test suite and manual UAT before declaring success.
Prove the fix works. "I think it works" is not evidence. Run the suite, show the output, then harden against recurrence.
Two-commit red/green policy (e45s08) — Bug fixes follow the same two-commit discipline as
develop-tdd: first commit adds/adjusts the failing test (test(<scope>): …), second commit applies the fix (fix(<scope>): …). Do not squash RED and GREEN before review.
Checklist
1. Re-run the originally failing test
# Run the specific test that captured the bug
<test command for the failing test>
- Previously failing test now passes
2. Run the full test suite
# Run all tests — no filtering
<full test command from CLAUDE.md>
- All tests pass (zero regressions)
3. Type check
<typecheck command>
- No type errors introduced
4. Lint
<lint command>
- No lint violations introduced
5. Harden against recurrence
For every bug fixed, add at least one prevention layer:
| Mechanism | When to use |
|---|---|
| Type guard | Input could be the wrong shape |
| Schema validation (Zod, Pydantic, etc.) | External data crossing a boundary |
| Invariant assertion | Internal state that must always hold |
| Lint rule | Pattern that's easy to repeat by mistake |
| Environment check at startup | Missing config causes silent failure |
- At least one hardening mechanism added
- Hardening mechanism is tested
5b. Generalize-fix (HARD GATE — e80s04 / GH #98)
Sweep the defect class across the codebase after local hardening — see REFERENCE-generalize-fix.md.
- Defect class documented (not just the one-line root cause)
- Grep sweep run and
match_countrecorded -
verify-generalize-sweep.shpasses on the artifact
6. Update the bug file and registry.yaml
Find the most recent specs/bugs/BUG-*.md file and append the resolution:
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.
- 1mo ago First seen · 148 lines · 56 tokens per session scan A e97fa54d5294
validate-fix is a skill published in the GitHub repository danielvm-git/bigpowers (268 stars, last pushed 28d ago), licensed MIT. It adds 56 tokens to every session and 1,351 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
tdd
This skill should be used when the user asks to "add a feature using TDD", "fix a bug with TDD", "do TDD", "red-green-refactor", "write a failing test first", "use test-driven development", "start TDD", "test first approach", "TDD loop", "TDD cycle", or mentions TDD workflow, baby steps, guessing game, or…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
nw-bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.