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 tobihagemann/turbo --skill apply-findingsgit clone --depth 1 https://github.com/tobihagemann/turboWrote 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/tobihagemann/turbo/apply-findings)<a href="https://agentmods.dev/skills/tobihagemann/turbo/apply-findings"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/apply-findings/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/tobihagemann/turbo/apply-findings"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/apply-findings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.01412 |
| Opus 5 | $0.00035 | $0.00706 |
| Sonnet 5 | $0.00014 | $0.00282 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
apply-findings 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 12d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Findings
Apply evaluated findings from the conversation context. Findings must have been through /evaluate-findings first.
Step 1: Identify Findings
Collect all findings from the conversation context. Findings should have Verdict columns (Apply, Skip, Escalate) from /evaluate-findings.
If findings are unevaluated (raw output without verdicts), stop and say to run /evaluate-findings first.
Step 2: Apply in File Order
Group Apply findings by file path and apply in file order to minimize context switching. For each finding:
- Read the full function or logical block at the referenced location
- Verify the finding still applies to the current code
- When the finding carries a suggested fix, treat the fix as a separate claim from the finding and verify it independently before applying it — trace it against the failure modes the finding names. When the fix encodes, escapes, quotes, or otherwise sanitizes untrusted input, enumerate the character classes the target interpreter treats specially and name the construct in the fix that blocks each one; a class with no blocker means the fix is incomplete, including when it reproduces the finding's suggested wording. If the fix does not hold up, treat the finding as Escalate (surface it in Step 3) and record why the remedy fails, rather than applying an unsound fix on the finding's authority.
- When the fix would reverse a decision the user made earlier — in discussion or recorded in the artifact — treat the finding as Escalate (surface it in Step 3) and name the original decision. Judge by the outcome rather than the wording of the option the user chose: a reversal leaves the user with something materially different from what they chose. When the finding refutes only the factual premise the user's choice rested on and the fix leaves the chosen outcome intact, that is a premise correction: confirm the refutation against whichever of the code, the governing artifact, or authoritative documentation the premise turns on, and when none settles it, treat the finding as Escalate. Otherwise continue with the remaining checks, and state both the corrected premise and the chosen outcome it leaves standing in Step 4.
- Check what the fix you are about to make changes about the inputs the code accepts. When the change in accepted inputs is exactly the defect the finding names, apply it normally. When it turns away or newly admits anything beyond that defect — a value or path a legitimate caller could send — that is a behavior change: treat the finding as Escalate (surface it in Step 3) and name the input class that changes.
- Make the fix
- If the finding renames an identifier or changes a recurring shape — a type signature, call pattern, or wrapper that appears in many places — search every caller and reference the change reaches, not only the changed files, by concept rather than by the literal just replaced: a stem that survives inflection and compounding, or the shape common to every variant. A clean search proves nothing when its pattern was derived from a single instance, and the cited location is often only one of several references. When the finding names several sites, also tick them off against the finding text. Complete the sweep before marking the fix complete.
- When the fix adds or edits a comment stating a contract — what is handled, what is excluded, what callers may rely on — verify the code enforces that contract before marking the fix complete. When it does not, add the enforcement rather than narrowing the comment.
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.
- 12d ago First seen · 64 lines · 70 tokens per session scan A 1a23234d6879
apply-findings is a skill published in the GitHub repository tobihagemann/turbo (402 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,412 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
agentic-review
Deep multi-agent code review for local changes. Inspired by AmpCode's agentic review. Use when you want comprehensive analysis of staged changes, unstaged changes, specific commits, or branch differences. Spawns parallel specialized agents (security, performance, patterns, architecture) and synthesizes actionable…
qa
Full QA on all session changes using Codex as a second pair of eyes. Use when user says "QA", "full QA", "QA my changes", "QA all your changes", or "use codex to review". Runs git diff, sends changes to Codex for thorough review, and synthesizes findings.
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.
zh-code-reviewer
A Chinese-language code-review specialist that produces a structured review report. It examines coding style, possible bugs, performance, security, and design choices.
review-implementing
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
code-auditor
Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.