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 klimentij/klimkit --skill klimkit-final-reviewergit clone --depth 1 https://github.com/klimentij/klimkitWrote 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/klimentij/klimkit/klimkit-final-reviewer)<a href="https://agentmods.dev/skills/klimentij/klimkit/klimkit-final-reviewer"><img src="https://agentmods.dev/badge/skills/klimentij/klimkit/klimkit-final-reviewer/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/klimentij/klimkit/klimkit-final-reviewer"><img src="https://agentmods.dev/badge/skills/klimentij/klimkit/klimkit-final-reviewer.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 | $0.00069 | $0.00372 |
| Opus 5 | $0.00034 | $0.00186 |
| Sonnet 5 | $0.00014 | $0.00074 |
| Haiku 4.5 | $0.00007 | $0.00037 |
Grade A, and why
klimkit-final-reviewer 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 9d 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.
What it actually says
Klimkit Final Reviewer
Use this only after the main agent believes the work is complete and has drafted the exact final response. Review; do not implement fixes.
Required Inputs
- Original user request or task path.
- Acceptance checklist when implementation was involved.
- Changed files and important diffs.
- Verification evidence and skipped checks.
- Reflection entry or explicit reflection-not-applicable note.
- Proof report path and URL for UI/proof work.
- Exact draft response that would be sent to the human.
Review Workflow
- Extract every concrete claim from the draft response.
- Verify each claim against the request, checklist, changed files, test output, release state, and proof artifacts.
- Confirm unavailable checks and residual risks are named accurately.
- For UI/proof work, inspect the report and media references when accessible.
- For non-trivial implementation, require
klimkit-reflectoroutput or a justified not-applicable note. - Return
KEEP WORKINGif any material claim is unsupported, contradicted, vague, incomplete, missing reflection, or missing required proof. - Return
READY FOR USERonly when the draft is fully supported.
Output
Use these sections:
User intentWhat is verifiedWhat is missing or not provenVerdictNext actions for main agent
The verdict must be exactly READY FOR USER or KEEP WORKING.
What ships with it
1 file 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.
- 9d ago First seen · 41 lines · 69 tokens per session scan A 86cd93dc0588
klimkit-final-reviewer is a skill published in the GitHub repository klimentij/klimkit (7 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 372 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 2026-08-31.
Other skills, from other repositories
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
critic-gate
Full execution protocol for MODE: CRITIC-GATE -- plan critic review, revision loops, and hard stop before execution.
swarm-pr-feedback
Codex adapter for closing known PR feedback in any repository. Use when asked to address pasted review feedback, GitHub review comments or threads, requested changes, CI/check failures, merge conflicts, stale PR branches, or follow-up work that must verify and close all known PR issues.
codebase-review-swarm
Codex adapter for running a rigorous, quote-grounded codebase review or security/QA/accessibility/performance/AI-slop/enhancement audit. Use for full-repo or large-subsystem review reports; not for normal implementation.
swarm-pr-review
Thin adapter for the canonical swarm-pr-review skill. The authoritative workflow lives in .opencode and this file only preserves the mirror contract for Codex-side skill discovery.