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 gvkhosla/compound-engineering-pi --skill ce-compound-refreshgit clone --depth 1 https://github.com/gvkhosla/compound-engineering-piWrote 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/gvkhosla/compound-engineering-pi/ce-compound-refresh)<a href="https://agentmods.dev/skills/gvkhosla/compound-engineering-pi/ce-compound-refresh"><img src="https://agentmods.dev/badge/skills/gvkhosla/compound-engineering-pi/ce-compound-refresh.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 5.1 | $0.00088 | $0.06778 |
| Opus 5 | $0.00044 | $0.03389 |
| Sonnet 5 | $0.00018 | $0.01356 |
| Haiku 4.5 | $0.00009 | $0.00678 |
Grade A, and why
ce:compound-refresh 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 7d 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 — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compound Refresh
Maintain the quality of docs/solutions/ over time. This workflow reviews existing learnings against the current codebase, then refreshes any derived pattern docs that depend on them.
Mode Detection
Check if $ARGUMENTS contains mode:autonomous. If present, strip it from arguments (use the remainder as a scope hint) and run in autonomous mode.
| Mode | When | Behavior |
|---|---|---|
| Interactive (default) | User is present and can answer questions | Ask for decisions on ambiguous cases, confirm actions |
| Autonomous | mode:autonomous in arguments |
No user interaction. Apply all unambiguous actions (Keep, Update, auto-Archive, Replace with sufficient evidence). Mark ambiguous cases as stale. Generate a summary report at the end. |
Autonomous mode rules
- Skip all user questions. Never pause for input.
- Process all docs in scope. No scope narrowing questions — if no scope hint was provided, process everything.
- Attempt all safe actions: Keep (no-op), Update (fix references), auto-Archive (unambiguous criteria met), Replace (when evidence is sufficient). If a write succeeds, record it as applied. If a write fails (e.g., permission denied), record the action as recommended in the report and continue — do not stop or ask for permissions.
- Mark as stale when uncertain. If classification is genuinely ambiguous (Update vs Replace vs Archive) or Replace evidence is insufficient, mark as stale with
status: stale,stale_reason, andstale_datein the frontmatter. If even the stale-marking write fails, include it as a recommendation. - Use conservative confidence. In interactive mode, borderline cases get a user question. In autonomous mode, borderline cases get marked stale. Err toward stale-marking over incorrect action.
- Always generate a report. The report is the primary deliverable. It has two sections: Applied (actions that were successfully written) and Recommended (actions that could not be written, with full rationale so a human can apply them or run the skill interactively). The report structure is the same regardless of what permissions were granted — the only difference is which section each action lands in.
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.
- 7d ago First seen · 538 lines · 88 tokens per session scan A c82c8a993e64
ce:compound-refresh is a skill published in the GitHub repository gvkhosla/compound-engineering-pi (51 stars, last pushed 4mo ago), licensed MIT. It adds 88 tokens to every session and 6,778 once invoked, about $0.0004 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
codex-claude-worker
Translate natural-language user requests into bounded Claude Code worker tasks while Codex or ChatGPT remains the supervisor. Use when the user gives an ordinary prompt and wants Codex to clarify scope, choose a safe work boundary, generate a worker prompt, approve or defer worker execution, read run summaries and…
write-swift
How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know…
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
source-research
Research open-source libraries with evidence-backed answers and GitHub permalinks. Use when the user asks about library internals, needs implementation details with source code references, wants to understand why something was changed, or needs authoritative answers backed by actual code. Excels at navigating large…
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
provider-model-discovery
Descobre e seleciona modelos de providers LLM de forma report-only: inventário read-only de modelos, docs oficiais, quota/billing/rate gates e shortlist para canary protegido. Use antes de adicionar providers, escolher modelos ou migrar monitores/roteamento.