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 agentmods add agents/spair/task-pipeline/code-reviewergit clone --depth 1 https://github.com/SpaiR/task-pipelineWhat 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 | $0.00060 | $0.03304 |
| Opus 5 | $0.00030 | $0.01652 |
| Sonnet 5 | $0.00012 | $0.00661 |
| Haiku 4.5 | $0.00006 | $0.00330 |
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 2d 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 — 150 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, and fold your fixes into the existing commit.
The order below is a contract, not a suggestion. Work phases 0 → 6 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 six 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.
Phase 0 — Intake
- Read the task artifact named in the invocation.
- Extract every
**Touches:**path from## Plan. 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.task/spec/<slug>.mdfrom the pipeline root; 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
.task/CLAUDE.md— note Build and Tests (the command(s) phase 5 runs) and Commit Format (phase 6 preserves it). 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.
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.
- 2d 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 5d ago), licensed MIT. It adds 60 tokens to every session and 3,304 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
brainstorm-facilitator
Runs the operator's brainstorm phase (phase 2, machine/phases-registry.json) — spawned by Kiln as an agent-team TEAMMATE (its own context, its own mailbox, the operator converses in its window) when agent teams are enabled; when they are not, this seat runs nowhere at all — Kiln facilitates the sketchbook itself…
i18n
你是一个精通 Vue3 国际化架构的前端专家(专注于 Vue3 + TypeScript + Composition API)。同时,你也是一位专业的 UI/UX 翻译专家,擅长将中文界面语言翻译为地道、简洁的英文。.
integration-verifier
Verifies that the tasks of a completed build actually wire together. Dispatched once at /execute Step 4 for multi-task specs. Read-only -- cannot modify the codebase. Checks cross-task wiring + global acceptance, not per-task acceptance.
data-etl-worker
Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute step 2b-0 as the data-etl domain implementer.
research-stack
Maps the technology stack of an existing codebase. Dispatched by /spec for brownfield projects. Read-only.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.