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-compoundnpx skills add EveryInc/compound-engineering-plugin --skill ce-compoundgit 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 | $0.00023 | $0.01482 |
| Opus 5 | $0.00012 | $0.00741 |
| Sonnet 5 | $0.00005 | $0.00296 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
ce-compound 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ce-compound
Outcome: one solved problem is written as a durable learning under <root>/solutions/, grounded against the current tree, discoverable by the next agent.
Done: the doc is written or updated, its frontmatter and claims validated, vocabulary capture recorded even when nothing qualified, and the mode's completion report emitted.
One learning per run. A session that produced several gets several sequential runs, never one batched run — references/research.md carries what batching breaks.
Preconditions
Document a problem that is solved, verified working, and non-trivial. These are advisory: judge them from the session rather than asking about them. When the session plainly holds no such problem, write nothing and report why.
ce-compound is not a CONCEPTS.md bootstrap tool — it seeds the learning's own area as a side effect, never the whole repo. Send a standalone request to create or bootstrap that file to ce-compound-refresh, then exit.
Mode Detection
/ce-compound [brief context]
/ce-compound mode:non-interactive depth:lightweight [context]
/ce-compound mode:non-interactive depth:full [context]
Enter non-interactive mode when either holds: the arguments you were invoked with contain the mode:non-interactive token or its deprecated alias mode:headless, or the invocation makes non-interactive intent unmistakable — a caller or standing instruction asking to run ce-compound "headless", "non-interactively", "unattended", or "without prompts/questions". Both tokens together is not a conflict. Bare "automatically" or "auto-run" is not on its own a non-interactive signal — it speaks to invoking the skill, not to suppressing its prompts — so an ambiguous or absent signal defaults to interactive. Tokens starting with mode: or depth: are flags, not context: strip them before treating the remainder as the brief context hint. Once detected, non-interactive mode applies for the entire run.
Depth is an explicit non-interactive-only selector, and at most one depth token is accepted. depth:lightweight routes directly to Lightweight Mode. depth:full or no depth token enters Full Mode, including its automatic session-history probe. A non-interactive call carrying no depth token therefore behaves as it always has. Non-interactive lightweight asks no blocking questions and launches no subagents. If the invocation carries an unknown depth: token, multiple depth: tokens, or a depth: token without non-interactive intent, do not guess: emit the non-interactive failure report with the reason and end with Documentation skipped.
What ships with it
26 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.
- assets/resolution-template.md 2.5 KB
- references/agents/best-practices-researcher.md 7.2 KB
- references/agents/data-integrity-guardian.md 3.1 KB
- references/agents/framework-docs-researcher.md 5.5 KB
- references/agents/pattern-recognition-specialist.md 3.6 KB
- references/agents/performance-oracle.md 4.5 KB
- references/agents/security-sentinel.md 4.0 KB
- references/agents/session-historian.md 7.0 KB
- references/assembly.md 14 KB
- references/concepts-vocabulary.md 8.8 KB
- references/enhancement.md 2.7 KB
- references/grounding-validation.md 6.7 KB
- references/lightweight.md 6.8 KB
- references/modes.md 1.6 KB
- references/refresh-and-discoverability.md 9.7 KB
- references/report.md 6.3 KB
- references/research.md 12 KB
- references/schema.yaml 8.7 KB
- references/session-history.md 8.4 KB
- references/yaml-schema.md 8.4 KB
- scripts/session-history/discover-sessions.sh 11 KB runs code
- scripts/session-history/extract-errors.py 9.1 KB runs code
- scripts/session-history/extract-metadata.py 20 KB runs code
- scripts/session-history/extract-skeleton.py 21 KB runs code
- scripts/validate-doc-claims.py 20 KB runs code
- scripts/validate-frontmatter.py 4.9 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.
- 2d ago First seen · 72 lines · 23 tokens per session scan A 90bce554fa6e
ce-compound is a skill published in the GitHub repository EveryInc/compound-engineering-plugin (24,760 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,482 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
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.