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 skills/everyinc/compound-engineering-plugin/ce-doc-reviewnpx skills add EveryInc/compound-engineering-plugin --skill ce-doc-reviewgit clone --depth 1 https://github.com/EveryInc/compound-engineering-pluginWrote 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/everyinc/compound-engineering-plugin/ce-doc-review)<a href="https://agentmods.dev/skills/everyinc/compound-engineering-plugin/ce-doc-review"><img src="https://agentmods.dev/badge/skills/everyinc/compound-engineering-plugin/ce-doc-review.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01438 |
| Opus 5 | $0.00014 | $0.00719 |
| Sonnet 5 | $0.00006 | $0.00288 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
ce-doc-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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Review
Review a requirements or plan document with a team of reviewer personas. Dispatch generic subagents, each seeded with a skill-local reviewer prompt. Synthesis sorts the findings: apply and report the ones it routes to Apply, in the document's native format, and route the rest to the user.
Done when: every dispatched reviewer returned or was named as failed in Coverage, the fixes routed to Apply are applied and reported, and the rest went through the four-option interaction (interactive) or came back as structured text with classifications intact (non-interactive).
Interactive mode rules
Read references/modes.md before anything else. It owns mode detection, the non-interactive argument contract, and the question-tool rules: match the host's blocking question tool already in the current tool list (never call a user-facing question tool to discover it), pre-load it at the top of the interactive flow if it is listed but unloaded, and fall back to a numbered list only when the harness genuinely lacks one.
Either way, a question that calls for a user decision fires the tool or falls back loudly. Narrating it as text is a bug.
Artifact Root
Resolve <root> only in the no-path interactive branch, which discovers the most recent plan under <root>/plans/. Every other run reads the document at the path it was handed. So an absolute-path or non-interactive review — /tmp/plan.md, possibly outside any repo — never depends on a repo root or a CE config it does not need.
Resolve the CE artifact root <root> before composing any artifact path.
- Read
docs_rootfrom<repo-root>/.compound-engineering/config.yamlonly (<repo-root>=git rev-parse --show-toplevel). Do not read it fromconfig.local.yaml. Unset -><root>isdocs, exactly as before. - Validate a set value: a repo-relative directory whose real, symlink-resolved path stays inside the repo and is neither the repo root nor under
.git/. Otherwise stop with an error namingdocs_rootand the value -- never fall back todocs. - Use
<root>as the sole artifact location: create it if absent, compose each path as<root>/<subdir>with this skill's own subdirectory, and never also readdocs.
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/bulk-preview.md 13 KB
- references/cross-model-eval.md 8.7 KB
- references/cross-model-review.md 33 KB
- references/decision-primer.md 3.1 KB
- references/dispatch.md 4.1 KB
- references/document-intake.md 5.0 KB
- references/findings-schema.json 5.1 KB
- references/modes.md 2.6 KB
- references/open-questions-defer.md 11 KB
- references/persona-selection.md 4.7 KB
- references/personas/adversarial-document-reviewer.md 11 KB
- references/personas/coherence-reviewer.md 11 KB
- references/personas/design-lens-reviewer.md 4.5 KB
- references/personas/feasibility-reviewer.md 6.0 KB
- references/personas/product-lens-reviewer.md 9.3 KB
- references/personas/scope-guardian-reviewer.md 6.1 KB
- references/personas/security-lens-reviewer.md 4.6 KB
- references/personas/whole-doc-reviewer.md 3.0 KB
- references/rendering-floor.md 13 KB
- references/review-output-template.md 13 KB
- references/subagent-template.md 30 KB
- references/synthesis-and-presentation.md 54 KB
- references/walkthrough.md 38 KB
- scripts/cross-model-doc-review.sh 63 KB runs code
- scripts/peer-job-runner.py 102 KB runs code
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.
- 4d ago First seen · 73 lines · 28 tokens per session scan A abac73d43796
ce-doc-review is a skill published in the GitHub repository EveryInc/compound-engineering-plugin (24,821 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,438 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
draft-openspec-docs
Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the user, then drafts one section per approved step and cleans up after itself. Use when a page needs a from-scratch rewrite or a new page is being shaped…
answer-processing
Use whenever the user uploads a hand-written or scanned answer PDF to be graded against a reference solution. Converts answer PDFs in answers/.pdf to markdown in answers/converted/.md using the pdf skill (OCR as needed), then performs strategy-based grading against converted/solutions/.md or quizzes/answers.md.…
Use whenever the user works with PDF files — reading/extracting text from PDFs (lecture notes, textbook chapters, HW problems, HW solutions, hand-written answers), converting PDFs to markdown for downstream analysis, merging/splitting PDFs, or creating PDFs. For scanned or hand-written PDFs, OCR is required…
vision-ocr
Use whenever a hand-written or scanned answer PDF needs transcription to markdown for /grade. Three tiers — Claude native vision (default, no extra install), local Qwen3-VL 8B via ollama (opt-in privacy mode), pytesseract fallback. The engine is selected via OCRENGINE in .course-meta (written by /paideia:init-course)…
engineering-rapid-prototyper
You are Rapid Prototyper, a specialist in ultra-fast proof-of-concept development and MVP creation. You excel at quickly validating ideas, building functional prototypes, and creating minimal v...
data-extraction-agent
Monitor designated Excel file directories for new or updated sales reports. Extract key metrics — Month to Date (MTD), Year to Date (YTD), and Year End projections — then normalize and persist them for downstream reporting and distribution.