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 beingmartinbmc/jambavan --skill strict-reviewergit clone --depth 1 https://github.com/beingmartinbmc/jambavanWrote 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/beingmartinbmc/jambavan/strict-reviewer)<a href="https://agentmods.dev/skills/beingmartinbmc/jambavan/strict-reviewer"><img src="https://agentmods.dev/badge/skills/beingmartinbmc/jambavan/strict-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/beingmartinbmc/jambavan/strict-reviewer"><img src="https://agentmods.dev/badge/skills/beingmartinbmc/jambavan/strict-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 | $0.00060 | $0.00799 |
| Opus 5 | $0.00030 | $0.00400 |
| Sonnet 5 | $0.00012 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
strict-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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strict Reviewer
Reviewing is not skimming for typos. Find what a lazy pass would miss: the wrong root cause, the abstraction nobody asked for, the claim with no evidence behind it.
Step 1 — Get the real diff, not a guess
If jambavan_review_pack is available, call it against the PR's base branch. It gives you touched files, parsed symbols changed or deleted in each, bounded extracted caller candidates, heuristic test associations/references, past failure records mentioning the same files, and risk flags (open // rin: debt, no matching test association). Treat graph and test associations as review leads, not proof of completeness.
Otherwise: git diff --stat first, then the full diff only for files that matter.
Step 2 — Root cause, not symptom
- Is this a fix for the actual bug, or a patch on the path the ticket happened to name?
- If a shared function was touched, were the relevant callers and public entry points checked? A guard added to one call site while an identified sibling caller stays broken is a review-blocking finding, not a nit.
- Does the change explain why, not just what? A diff that only patches the symptom should be flagged even if it "works."
Step 3 — Scope discipline
Flag, don't just note, when a diff contains:
- An abstraction with exactly one implementation (interface/factory for a single case).
- A new dependency where the stdlib or an already-installed package would do.
- Boilerplate or scaffolding nobody asked for.
- Changes broader than the stated problem — "while I was in there" edits to unrelated code.
- A shortcut with no
// rin:marker naming its ceiling and upgrade path (or a// rin:marker used to excuse actual sloppiness rather than a conscious tradeoff).
Not negotiable, regardless of diff size: input validation at trust boundaries, error handling that prevents data loss, security, accessibility, and anything the original request explicitly asked for. A "small diff" is not an excuse to skip these.
Step 4 — Demand evidence, not assertions
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 · 51 lines · 60 tokens per session scan A 1fa17c0d868d
strict-reviewer is a skill published in the GitHub repository beingmartinbmc/jambavan (2 stars, last pushed 8d ago), licensed MIT. It adds 60 tokens to every session and 799 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
lean-debt
A read-only scanner for intentional simplification markers in a code repository. These markers record code that has a known limit and should be revisited when a stated condition occurs.
lean-review
A review focused only on code that may be more complicated than needed. It identifies candidates for deletion, standard-library or built-in replacements, and shorter equivalent code.
code-review
A checklist for reviewing code changes before they are merged into a shared codebase. It checks whether the changes match the request and follow project rules.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
pr-body
A tool that reviews all commits on the current branch and creates or updates a pull request title and description. A pull request is a proposed code change submitted for review.
agentsight-code-review
A review checklist for changes in the AgentSight codebase, compared with the main branch. It checks coding rules, eBPF safety, C-language interfaces, code-size growth, and tests.