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/stacklok/toolhive-studio/bug-fix-tddnpx skills add stacklok/toolhive-studio --skill bug-fix-tddgit clone --depth 1 https://github.com/stacklok/toolhive-studioWhat 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 | $0.00052 | $0.01679 |
| Opus 5 | $0.00026 | $0.00839 |
| Sonnet 5 | $0.00010 | $0.00336 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
bug-fix-tdd 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fix TDD
Reproduce bugs with a failing test, then apply the minimum fix. This skill is used by the automated bug-fix agent in CI but can also be invoked manually.
TDD Workflow
Phase 1 — Analysis & Failing Test (Red)
- Parse the bug report: extract description, steps to reproduce, expected vs actual behavior
- Find relevant code: use Grep/Glob to locate the component, hook, or route mentioned in the bug
- Write a unit test that reproduces the bug — the test MUST FAIL
- Run the test:
pnpm run test:nonInteractive -- <test-file-path> - Verify failure reason: the test must fail because of the bug, not because of import errors or unrelated issues
- Retry if needed: if the test passes (bug not reproduced), try a different approach (max 3 attempts)
- Write
bug-analysis.mdwith findings (see format below)
Constraints: Do NOT modify source files in Phase 1. Only create/edit test files and bug-analysis.md.
Phase 2 — Fix (Green)
- Read the failing test and
bug-analysis.md - Apply the MINIMUM fix to make the test pass — do not over-engineer
- Run the single test:
pnpm run test:nonInteractive -- <test-file-path> - Run the full suite:
pnpm run test:nonInteractive - Run static checks:
pnpm run lintandpnpm run type-check - Retry if needed: if any check fails, adjust the fix (max 5 attempts)
- Write
pr-body.mdandfix-title.txt
Constraints: Do NOT run git, gh, or modify .env files.
Phase 2b — Direct Fix (Fallback)
If Phase 1 cannot reproduce the bug in a test (test passes after 3 attempts), Phase 2b runs instead of Phase 2.
- Read
bug-analysis.mdandissue-body.mdfor context - Apply the MINIMUM fix based on code analysis alone
- If you CAN write a regression test, do so — but it is not required
- Run the full suite:
pnpm run test:nonInteractive - Run static checks:
pnpm run lintandpnpm run type-check - Retry if needed: if any check fails, adjust the fix (max 5 attempts)
- Write
pr-body.mdandfix-title.txt— note in the PR body that no regression test was possible
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 · 211 lines · 52 tokens per session scan A 080ff2527ac1
bug-fix-tdd is a skill published in the GitHub repository stacklok/toolhive-studio (163 stars, last pushed 4d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,679 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
tdd
For this repo, TDD means: fixtures first, then rule, then record validation.
implement
Write the production code that makes a pre-decided set of failing tests pass, within an explicit writeset, following an explicit behavior contract. Used by /tdd Step 3 and by /swarm-dispatch workers. The caller has already decided architecture, naming, file layout, and abstraction boundaries — this skill executes that…
scenario
Write executable failing tests from a recipe handed to you by the main context. Used by /tdd Step 2 and ad-hoc when a phase needs tests-first to drive implementation. Decisions about which scenarios to cover, which categories matter, and which fixtures to use are made by the caller — this skill executes that recipe…
post-cutoff-api-repair
Use when a held-out task needs the new LedgerAuth API name.
test-driven-development
Red-green-refactor discipline. Use when writing new functionality.
agent-integration
Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…