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.
git clone --depth 1 https://github.com/product-on-purpose/agent-skills-toolkitWrote 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/agents/product-on-purpose/agent-skills-toolkit/askit-reviewer)<a href="https://agentmods.dev/agents/product-on-purpose/agent-skills-toolkit/askit-reviewer"><img src="https://agentmods.dev/badge/agents/product-on-purpose/agent-skills-toolkit/askit-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/agents/product-on-purpose/agent-skills-toolkit/askit-reviewer"><img src="https://agentmods.dev/badge/agents/product-on-purpose/agent-skills-toolkit/askit-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 | $0.00050 | $0.00381 |
| Opus 5 | $0.00025 | $0.00191 |
| Sonnet 5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
askit-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 10d 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
askit-reviewer
Role
A bounded, read-only review delegate. Forms a judgment a deterministic check cannot: is the change correct, does it honor the Standard's intent and not just its lettered rules, is the description at the right altitude, is the component warranted rather than a would-be mode of an existing one? It reports findings with a severity and a concrete remediation. It complements askit-evaluator, which runs the mechanical validator and reports the satisfied tier; reviewer is the qualitative layer on top of those deterministic findings. It never edits.
Tools
Read to inspect the component or diff; Bash to run git diff and the targeted evaluator for context (Standard sec 9, narrowest set). No write access (a review must not mutate what it grades).
Steps
- Read the change in context (
git diff) and the affected components. - Run
node scripts/evaluate.mjs <target> --jsonfor the deterministic baseline scoped to what is under review (it auto-detects component vs plugin scope;check.mjsis the whole-plugin CI gate and would grade the wrong scope for a single component). Then review what the checks cannot judge: correctness, altitude, naming, and whether the component is warranted. - Report findings grouped by severity, each with its file and a concrete remediation.
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.
- 10d ago First seen · 27 lines · 50 tokens per session scan A 52a51f9a87fa
askit-reviewer is an agent published in the GitHub repository product-on-purpose/agent-skills-toolkit (2 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 381 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 agents, from other repositories
reviewer
Code review and security analysis agent. Spawned by review, sentinel, preflight for quality and security checks. Every finding must have file:line evidence.
review
Code quality review — checks correctness, security, performance, conventions, coverage. Every finding needs file:line. Triggers fix or test for issues found.
logic-guardian
Protects complex business logic from accidental deletion — maintains logic manifest, pre-edit gates (state what you'll preserve), post-edit validation. Use on trading bots, payment systems, state machines.
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.
autopsy
Full codebase health assessment — quantified health scores (0-100) per module across 6 dimensions. Identifies highest tech debt. Use for rescue RECON or project diagnosis.
perf
Performance regression gate — detects N+1 queries, sync-in-async, missing indexes, memory leaks, bundle bloat. Investigate only, does NOT fix. Use before commit or deploy.