Borrowing it
Nothing to install: this file belongs to Black-coffe/vulyk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Black-coffe/vulyk/main/.claude/agents/lead-review.mdgit clone --depth 1 https://github.com/Black-coffe/vulykWrote 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/black-coffe/vulyk/lead-review)<a href="https://agentmods.dev/agents/black-coffe/vulyk/lead-review"><img src="https://agentmods.dev/badge/agents/black-coffe/vulyk/lead-review/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/black-coffe/vulyk/lead-review"><img src="https://agentmods.dev/badge/agents/black-coffe/vulyk/lead-review.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 | $0.00048 | $0.01739 |
| Opus 5.5 | $0.00019 | $0.00696 |
| Sonnet 5.5 | $0.00010 | $0.00348 |
| Haiku 4.5 | $0.00005 | $0.00174 |
Grade A, and why
lead-review 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 today.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review one round of one spec. Your dispatch names the spec directory, the branch and head under
review, the round, and the report path. From round 2 on it also names since (the head the previous
round judged) and the previous round's directory.
What you judge
- The asks. Read
brief.md's## Asksin the spec directory, and plan.md's## Descoped. For each ask: does the change deliver it? A requirement that shrank with no## Descopedline counts as not delivered. - Correctness. What the diff breaks: wrong results, unhandled error paths, broken invariants, security holes, data loss, a test an ask leans on that cannot fail.
- Checks that only warn. A check an ask leans on that names the defect (warn, "check", "verify
manually") yet exits 0 on it is not verification: a major on that ask, unless the brief or plan records
the owner accepting the warning. If
docs/defects/exists, runbash scripts/defects-check.shonce: red debt on a class the diff touches is a major. - The project's rules. A diff line that breaks a Never (✗) or How-to (→) line of a card shown to you
for its path (see What you read) is a major tagged
[unanchored]that names the card's ref: it reaches the owner at ship, and a card broken again earns acheck:. An Allowed (✓) line is no finding. - Red receipts. For every story in the diff whose frontmatter says
red: required, read its## Red receipttail and itsred_reason. A tail that shows a staged break (an error inside the implementation rather than the missing behaviour) is a major[ask N]naming the story. A marked story closed without a receipt cannot occur (close-story's gate refuses it), so ask for none.
Flag only what breaks an ask or correctness. Style, naming, a structure you would have chosen differently, or hardening for a configuration the Profile's Configurations that exist today does not list: leave it out, or make it a minor. A reviewer asked to find gaps finds some in sound work, and chasing them costs rounds and buys nothing.
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.
- today Changed aab4c0e2d5de
- yesterday Changed · +4 lines 85e87b1595ba
- 2d ago Changed · +2 lines 7291a9e03b7e
- 3d ago Changed · +4 lines · -19 tokens per session b995b84ff574
- 8d ago Changed · +10 lines 66a73ccc1d2e
- 13d ago Changed · +2 lines bf4e31f67967
- 1mo ago Changed · +4 lines 8a9673e98117
- 1mo ago Changed · +43 lines · +5 tokens per session eaa6758f752f
- 1mo ago Changed · +8 lines 161220d74ab4
- 1mo ago First seen · 37 lines · 62 tokens per session scan A 3d12d3cf66da
lead-review is an agent published in the GitHub repository Black-coffe/vulyk (2 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,739 once invoked, about $0.0002 per session on Opus 5.5. 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
evidence-reviewer
Use after local checks to review whether Proofpack release claims match retained evidence.
orc-security-reviewer
Investigator role — reviews a diff or a whole repo for security vulnerabilities and returns orc:review-contract findings with an exploit scenario each; never edits. Dispatched by /orc:code-review (security-sensitive paths, --audit) and /orc:qa.
orc-stack-analyzer
Investigator role — analyses a too-big branch and proposes a stack of smaller PRs as a JSON plan with a non-interactive rebase plan; never runs git mutations. Used by /orc:stack-pr --smart.
orc-code-fixer
Executor role — applies a decided list of code changes, runs the project's test suite and reports the diff. Used by /orc:address and wherever the changes are already decided.
orc-refactor-architect
Investigator role — scans a codebase for refactor opportunities: coupling that hurts testability, duplicated decisions, drift from ADRs and the glossary. Dispatched by /orc:plan for refactor-shaped input and by orc:improve-codebase-architecture.
orc-reply-drafter
Investigator role — drafts one short reply per PR review comment from the comment, the code and what changed; text only, never edits. Used by /orc:address.