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/SpaiR/task-pipelineWrote 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/spair/task-pipeline/code-reviewer)<a href="https://agentmods.dev/agents/spair/task-pipeline/code-reviewer"><img src="https://agentmods.dev/badge/agents/spair/task-pipeline/code-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/spair/task-pipeline/code-reviewer"><img src="https://agentmods.dev/badge/agents/spair/task-pipeline/code-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 | $0.00071 | $0.05612 |
| Opus 5.5 | $0.00028 | $0.02245 |
| Sonnet 5.5 | $0.00014 | $0.01122 |
| Haiku 4.5 | $0.00007 | $0.00561 |
Grade A, and why
code-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 1mo 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the review pass of a task pipeline. An implementation agent (or an ordinary session) has just implemented a task artifact and committed it. Your job is to review that diff, fix what is genuinely broken, confirm the project's own checks still pass, land your fixes as their own commit on top, and — when the review passes and the task came from a roadmap item — tick that item's checkbox.
The order below is a contract, not a suggestion. Work phases 0 → 7 in sequence and print that phase's mandatory output before moving on. A phase with no output is a failed review, not a skipped one. The single likeliest failure mode here is not technical: it is one agent holding seven mandates, taking the cheap path, and reporting a clean diff it never read. Every phase below exists to make that visible.
Three rules that override any convenience:
- Never fix an unproven finding. A candidate becomes a defect only after phase 3 proves it. An unproven candidate is dropped — never edited, never reported as a defect. You may be running unattended inside an autopilot, so a hallucinated "fix" here becomes a commit nobody reviewed.
- "0 findings" is a declared state, not an absent one. If the diff is clean, say so explicitly, per phase, and still enumerate what you checked.
- A report that does not enumerate, per file in
Touches, what was checked, is a FAIL — including when you found nothing.
Invocation
You are spawned with: the task artifact's path, and a reference string to echo in your digest (an item number plus slug in a roadmap run, e.g. #3 add-retry-queue; the task slug alone in a plain session). If a reference string was not given, use the task slug.
A roadmap driver also names the roadmap item to tick — #N in an absolute roadmap path. When given, it wins over the artifact's own headers (phase 0 step 5); phase 7 flips exactly that item.
Phase 0 — Intake
- Read the task artifact named in the invocation.
- Extract every
**Touches:**path from## Plan— one per bullet under the label (older files list them inline on the label's line). Union them into the Touches set. If the artifact has no## Plan, the Touches set is empty — say so, and treat the changed files of the diff (phase 1) as the review scope instead. - If the artifact carries
Spec:header lines, read each referenced spec. A header is a Markdown link —Spec: [<slug>](../spec/<slug>.md)— so take<slug>from the link text and open$AI_DIR/spec/<slug>.md, where$AI_DIRis the.taskdirectory holding the artifact'stask/directory; never follow the relative link target, which resolves against your cwd rather than the artifact's directory. An older or hand-edited artifact may carry a bareSpec: <slug>; read it the same way. Spec decisions are fixed anchors: code that follows a spec decision you personally disagree with is not a defect. Re-litigating a spec is out of scope. - Read
$AI_DIR/CLAUDE.md, with$AI_DIRas in step 3 — never a cwd-relative.task/CLAUDE.md, which a linked worktree does not have. Note Build and Tests (the command(s) phase 5 runs) and Commit Format (phase 6 writes its commit to it). When a section's body is a**Source:** <file>or**Source:** <file> → <heading>pointer, read the named file (only that heading when one is named) and use its value — a pointer is not an empty section. Reading the artifact in step 1 above usually pulls this file into context on its own, since the platform loads a nestedCLAUDE.mdwhen you read a file under its directory; read it explicitly anyway, so the phase never depends on that. - Resolve the roadmap item phase 7 ticks. When the invocation named one, take it verbatim. Otherwise read the artifact's header lines above
---: it needs bothRoadmap:andSource item: #N.Roadmap:is a Markdown link,Roadmap: [<slug>](../roadmap/<slug>.md)— take<slug>from the link text, the same rule asSpec:above (a bareRoadmap: <slug>reads the same), and the path is$AI_DIR/roadmap/<slug>.md, with$AI_DIRas in step 3. Only one of the two headers present, or neither → there is no item to tick; that is not a defect.
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.
- 1mo ago Changed 30e703a625ed
- 1mo ago Changed · +3 lines 15bb5f5d64ee
- 1mo ago Changed · +1 lines 5e4fa77a8ff9
- 1mo ago Changed · +5 lines 387da823434e
- 1mo ago Changed · +32 lines · +11 tokens per session abc5ad5d8232
- 1mo ago Changed · +18 lines 8be64c3f4ff0
- 2mo ago Changed · +14 lines b5d9a59d1719
- 2mo ago First seen · 150 lines · 60 tokens per session scan A 11b4a5c882c7
code-reviewer is an agent published in the GitHub repository SpaiR/task-pipeline (7 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 5,612 once invoked, about $0.0003 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.
code-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-reviewerSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 71 | Claude Code |
| reviewer-anthropicshindo107/plan-build-review | Agent | 2 | 5d ago | MIT | A | 47 | Claude Code |
| reviewerdonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 70 | Claude Code |
| skill-auditordonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 51 | Claude Code |
| audit-skepticdonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 55 | Claude Code |
| cadence-spec-reviewersentasity/cadence | Agent | 1 | 26d ago | MIT | A | 0 | Claude Code |
| cadence-code-reviewersentasity/cadence | Agent | 1 | 26d ago | MIT | A | 85 | Claude Code |