Compound Engineering is a plugin that organizes software work into brainstorming, planning, implementation, review, and recording lessons for future changes. It is used with AI coding agents including Claude Code, Cursor, and Codex, and the catalogue entries provide parts of its agent, skill, command, and hook workflow.
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 skills add EveryInc/compound-engineering-plugin --skill ce-debuggit 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-debug)<a href="https://agentmods.dev/skills/everyinc/compound-engineering-plugin/ce-debug"><img src="https://agentmods.dev/badge/skills/everyinc/compound-engineering-plugin/ce-debug/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/skills/everyinc/compound-engineering-plugin/ce-debug"><img src="https://agentmods.dev/badge/skills/everyinc/compound-engineering-plugin/ce-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 11 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 48 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 76 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00023 | $0.03826 |
| Opus 5.5 | $0.00009 | $0.01530 |
| Sonnet 5.5 | $0.00005 | $0.00765 |
| Haiku 4.5 | $0.00002 | $0.00383 |
Grade A, and why
ce-debug 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 22d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug and Fix
Find the root cause of a failure, then — when the user chooses to — fix it with test-first discipline.
Done when: the causal chain from trigger to symptom is stated with no gaps and file:line evidence, and either a verified fix has been handed off (PR, commit, or the user's chosen stop) or a diagnosis-only summary has been delivered. Escalate rather than persist: 2-3 hypotheses exhausted without confirmation, or 3 failed fix attempts, means diagnose why instead of trying again — that is the smart escalation references/investigate.md describes. One hypothesis, one change at a time; changing several to see what helps is shotgun debugging.
<bug_description> is whatever this skill was invoked with — a failure description, a mode: token, or an issue reference (#123, org/repo#123, an issue URL) — from the user or from a calling skill (ce-babysit-pr / lfg in mode:pipeline pass the failing jobs and log tails; lfg's defect route passes mode:return-to-caller and the user's own reference). Blank if nothing was provided.
Mode
Default is interactive: investigate, run the Phase 2 fix-choice gate, then the Phase 4 handoff.
mode:pipeline (set by an orchestrator such as ce-babysit-pr or lfg): run fully non-interactively and never call the blocking-question tool. Strip the token from <bug_description>, then read references/pipeline-mode.md and follow it — it overrides every "ask the user" point with a conservative default, replaces the Phase 2 fix-gate with "fix convergent bugs, defer divergent ones", and replaces the Phase 4 handoff with a structured return whose status is exactly one of fixed-and-pushed | fixed-not-pushed | diagnosed-no-fix | flaky-infra | needs-human. The caller branches on those exact spellings, so never rename, abbreviate, or add to them.
mode:return-to-caller (set by lfg on its defect route): run non-interactively, but the caller owns everything after the fix. Strip the token, then read references/return-to-caller.md and follow it — it keeps Phases 0-3 and the convergent-or-defer fix boundary, applies the Phase 3 branch rule so the fix lands on a feature branch, commits the fix-owned files without pushing, skips the post-fix polish and review steps, and returns a structured result whose status is exactly one of fixed | diagnosed-no-fix | needs-human | blocked. The same spelling rule applies.
What ships with it
8 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.
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.
- 22d ago Changed 82540da83cbe
- 1mo ago Changed 32cf2ecee7cc
- 1mo ago Changed · +2 lines 1e125624007c
- 1mo ago Changed fa94434649d6
- 1mo ago Changed a09b72af1e74
- 1mo ago Changed bd5f1df5f1c6
- 1mo ago Changed · +4 lines · +2 tokens per session 4acacd966cf7
- 1mo ago First seen · 117 lines · 21 tokens per session scan A c1242bd85d57
ce-debug is a skill published in the GitHub repository EveryInc/compound-engineering-plugin (25,625 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 3,826 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
vigil-instrument
Instrument a service with OpenTelemetry — RED metrics, structured logs, distributed tracing, and health checks. Outputs actual code and config, not a plan. Use when asked to "add monitoring", "instrument this", "add logging", "set up tracing", or "observability".
apex-diagnose
Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent…
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
prism-audit
Frontend audit — bundle size, dependencies, accessibility, performance, component quality. Use when asked for "frontend review", "performance audit", "accessibility check", or "bundle size".
touch-audit
Mobile audit — app size, startup time, crash reporting, store compliance, accessibility, offline behavior. Use when asked for "mobile review", "app store readiness", "mobile performance", or "crash analysis".
vigil-incident
Incident response — diagnose production issues, find root cause, propose fix with rollback. Use when asked about "something is broken", "production issue", "why is this down", "incident", or "debug production".