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-code-reviewnpx skills add EveryInc/compound-engineering-plugin --skill ce-code-reviewgit clone --depth 1 https://github.com/EveryInc/compound-engineering-pluginWhat 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 | $0.01507 |
| Opus 5 | $0.00030 | $0.00754 |
| Sonnet 5 | $0.00012 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
ce-code-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 yesterday.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Artifact Root
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.
Execution spine
Follow these steps in order; the references supply the detail but never change the order. Each reference named below is a required read for its step: load it before doing that step's work.
- Read
references/modes-and-output.mdfirst. It settles what the arguments mean, which argument conflicts stop the run before any reviewer is dispatched, whether the quick-review short-circuit applies, and what this invocation returns. - Stage 1. Read
references/scope.mdand resolve the reviewed diff, the scope mode, and the deterministic scope signals. - Stage 2. Read
references/intent-and-plan.md, write the intent summary every reviewer receives, and discover the plan Stage 6 verifies requirements against. - Stage 3. Read
references/persona-catalog.mdandreferences/select-and-route.md, then select the risk-driven reviewer roster, discover applicable standards paths, and bind the adversarial route. - Stage 3d. When adversarial is selected for a local reviewed tree, start and persist the sanctioned cross-model job that
references/cross-model-review.mddefines, before any local persona dispatch. Invoking this skill is itself the authorization for its configured or allowlisted peer route, once you have made the required disclosure of the recipient and of the code that leaves the machine. Do not ask the user to confirm a second time, and do not skip the peer because the user did not repeat that authorization. An explicit user prohibition on external review overrides it, as does a checkout that setscross_model_review_mode: offwith no live opt-in; both are resolved before you bind a route. This pass's skip and target-selection keys arecross_model_review_modeandcross_model_peer. Missing files or unset keys take the default auto route; they are not a skip. Another skill's engine preference is not this gate. Model and effort overrides stay with the bound target as the reference states. A started peer replaces the local adversarial persona at this stage, and only a real failure to scope, allowlist, reach, authenticate, or start it leaves the local fallback in the roster; a later stage may still restore the local reviewer under the conditions that reference states. - Stage 4. Read
references/dispatch-reviewers.md. Dispatch the materialized local roster as one foreground concurrent batch sized to the host's active-agent cap. Every successful launch is collected when its terminal outcome is in hand: consume valid compact returns, classify a terminal tool error or malformed output as a failed reviewer, and keep launch receipts uncollected. Use the host's blocking collection capability for asynchronous receipts, and do not synthesize until every successful launch is collected. If launched work cannot be collected reliably, stop it, discharge any persisted peer through its owning cleanup before returning the failure result, and never emit progress or wait for a notification. Detaching local review into a polled background job is forbidden. The cross-model peer is the only detached work, and it may overlap this batch. - Stages 5 and 6. Once the reviewer returns are ready, read
references/finish-review.md. Fold in the peer once, run the documented findings mechanics, and run every validator the reference selects; only then return the report. Never synthesize directly from raw reviewer artifacts. In the multi-agent path, emit only this skill's report: do not also invoke a harness-native findings or reporting tool, which belongs to the quick-review short-circuit alone.
What ships with it
36 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/action-class-rubric.md 3.2 KB
- references/cross-model-eval.md 4.2 KB
- references/cross-model-review.md 33 KB
- references/diff-scope.md 4.9 KB
- references/dispatch-reviewers.md 19 KB
- references/findings-schema.json 6.3 KB
- references/finish-review.md 39 KB
- references/intent-and-plan.md 6.8 KB
- references/modes-and-output.md 5.4 KB
- references/persona-catalog.md 7.2 KB
- references/personas/adversarial-reviewer.md 10 KB
- references/personas/agent-native-reviewer.md 9.2 KB
- references/personas/api-contract-reviewer.md 3.7 KB
- references/personas/correctness-reviewer.md 5.6 KB
- references/personas/data-migration-reviewer.md 4.9 KB
- references/personas/deployment-verification-agent.md 4.9 KB
- references/personas/julik-frontend-races-reviewer.md 3.6 KB
- references/personas/learnings-researcher.md 16 KB
- references/personas/maintainability-reviewer.md 5.9 KB
- references/personas/performance-reviewer.md 3.5 KB
- references/personas/previous-comments-reviewer.md 3.3 KB
- references/personas/project-standards-reviewer.md 7.4 KB
- references/personas/reliability-reviewer.md 3.8 KB
- references/personas/security-reviewer.md 3.7 KB
- references/personas/swift-ios-reviewer.md 11 KB
- references/personas/testing-reviewer.md 4.9 KB
- references/review-output-template.md 14 KB
- references/scope.md 11 KB
- references/select-and-route.md 17 KB
- references/subagent-template.md 24 KB
- references/validator-batch-template.md 1.5 KB
- references/validator-template.md 5.6 KB
- scripts/cross-model-adversarial-review.sh 59 KB runs code
- scripts/findings-mechanics.py 8.7 KB runs code
- scripts/peer-job-runner.py 99 KB runs code
- scripts/review-scope.py 6.8 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.
- yesterday First seen · 42 lines · 60 tokens per session scan A 4fe803c556d4
ce-code-review is a skill published in the GitHub repository EveryInc/compound-engineering-plugin (24,696 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 1,507 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 2026-08-30.
Other skills, from other repositories
add-community-extension
Add a community extension to the Spec Kit catalog from a GitHub issue submission. USE FOR: processing extension submission issues, validating catalog entries, updating catalog.community.json and docs/community/extensions.md, creating PRs. DO NOT USE FOR: creating new extensions from scratch, or first-party extension…
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
release-openspec
Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is…
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.