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 adtn0810/truestack --skill truestack-quality-controlgit clone --depth 1 https://github.com/adtn0810/truestackWrote 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/adtn0810/truestack/truestack-quality-control)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-quality-control"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-quality-control/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/adtn0810/truestack/truestack-quality-control"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-quality-control.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 | $0.00148 | $0.01408 |
| Opus 5 | $0.00074 | $0.00704 |
| Sonnet 5 | $0.00030 | $0.00282 |
| Haiku 4.5 | $0.00015 | $0.00141 |
Grade A, and why
truestack-quality-control 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 11d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-quality-control
The gate between "I wrote it" and "it's done". Right-size the sweep to the diff: for a
trivial, output-neutral change (rename, comment, copy tweak) run tests + types/lint + intent
and declare that scope in the report; for anything touching logic, data, dependencies, or
boundaries, run every layer — a partial pass without that declaration is a fail.
First, read the intent (task, acceptance criteria, plan) and project memory (CLAUDE.md +
.ai/memory/) so you're judging against the real goal, not a guess. Tooling is
per-language — see references/tooling.md for the test / type-check / lint / perf /
security tools for Node, .NET, and Python.
1. Tests (review tests first)
Detect the framework (jest/vitest, pytest, dotnet test) and run the suite. Before trusting
them, check the tests themselves: do they exercise behavior through public interfaces, and
would they actually fail if the feature regressed? If changed code has no tests, write them
— happy path plus the edge cases the change touches. For data-accuracy-critical logic, add
property-based or invariant tests (properties that must hold across all inputs), not
just example cases — "all tests passed" is not the same as "matches intent". Any test
skipped, weakened, or deleted is a finding.
2. Type-check + lint
Run the type checker (tsc/mypy/.NET analyzers) and linter (eslint/ruff). Fix violations at the source — never suppress a warning to make it pass; a suppression is a deferred bug.
3. Review across six axes
Read the diff and classify every finding by severity (Critical = security / data-loss / broken behavior · Required = must fix before done · Optional · Nit):
- Correctness — requirements, edge cases, errors, concurrency, state.
- Maintainability — clear names, simple control flow, no dead code, no one-use abstractions; do a simplify pass (can duplicated logic merge? can a layer go without losing clarity?).
- Architecture — ownership, small interfaces, validation at boundaries, dependency direction.
- Security — OWASP Top 10: injection, broken auth/access control, secrets, untrusted input.
- Performance — unbounded work, N+1, hot paths.
- Tests — evidence matches risk. Lead with high-impact findings; one real issue beats a long list of nits.
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.
- 11d ago First seen · 98 lines · 148 tokens per session scan A 8051c2a20f41
truestack-quality-control is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 1,408 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".