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 aegntic/compound-engineering --skill compound-refreshgit clone --depth 1 https://github.com/aegntic/compound-engineeringWrote 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/aegntic/compound-engineering/compound-refresh)<a href="https://agentmods.dev/skills/aegntic/compound-engineering/compound-refresh"><img src="https://agentmods.dev/badge/skills/aegntic/compound-engineering/compound-refresh/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/aegntic/compound-engineering/compound-refresh"><img src="https://agentmods.dev/badge/skills/aegntic/compound-engineering/compound-refresh.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.03908 |
| Opus 5.5 | $0.00009 | $0.01563 |
| Sonnet 5.5 | $0.00004 | $0.00782 |
| Haiku 4.5 | $0.00002 | $0.00391 |
Grade A, and why
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 1mo 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 — 453 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. Review existing learnings against the current codebase, then refresh any derived pattern docs that depend on them.
Mode Detection
Check if $ARGUMENTS contains mode:autonomous. If present, strip it from arguments and run in autonomous mode.
| Mode | When | Behavior |
|---|---|---|
| Interactive (default) | User is present and can answer questions | Ask for decisions on ambiguous cases and confirm disruptive actions |
| Autonomous | mode:autonomous in arguments |
No user interaction. Apply unambiguous actions, mark ambiguous cases stale, and generate a full report |
Autonomous mode rules
- Skip all user questions.
- Process all docs in scope. If no scope hint was provided, process everything.
- Attempt all safe actions: Keep, Update, auto-Archive, and Replace when evidence is sufficient.
- If a write succeeds, record it as applied.
- If a write fails, record it as recommended in the report and continue.
- If classification is genuinely ambiguous, mark the doc stale with
status: stale,stale_reason, andstale_date. - Use conservative confidence. Borderline cases become stale in autonomous mode.
- Always generate a report with Applied and Recommended sections.
Local Grounding
Before editing anything under docs/solutions/, read the local guidance files in this order:
AGENTS.mdCLAUDE.md(if present)README.md
Use them to preserve the repository's docs conventions, OpenViking guidance, and workflow naming.
Interaction Principles
These principles apply to interactive mode only. In autonomous mode, skip all user questions and apply the autonomous rules above.
Follow the same interaction style as /workflows:brainstorm:
- ask questions one at a time
- prefer multiple choice when natural options exist
- start with scope and intent, then narrow only when needed
- do not ask the user to decide before you have evidence
- lead with a recommendation and explain it briefly
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.
- 1mo ago First seen · 453 lines · 22 tokens per session scan A 04664f1c4bef
compound-refresh is a skill published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 3,908 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 2026-08-31.
Other skills, from other repositories
PlanGate 決定論的 GC 判定
A rule-based checker that decides whether stored files, logs, and other review records should be kept or removed. It applies retention limits and safety exceptions to a supplied file list.
Closure Scope Retention Guard
Detects long-lived objects (caches, listeners, singletons) that capture an entire enclosing scope via closures/environment capture, keeping large arrays or buffers alive, and proposes copying only the needed fields.
walk
Query the graph. Semantic search + topology operations. The model's primary navigation tool over the vault.
dream
Push synthesis back at the user. Daily mode pulls 3 connections + 1 pattern + 1 question from recent activity. Weekly mode surfaces emerging thesis, contradictions, gaps, and one action. The feedback loop that turns the vault from input-store into thinking-partner.
learn
Full ingestion of a source. Composes /extract → /connect → /audit end-to-end. The verb you use when you want a source to land properly in the graph.
connect
Wire a note into the graph. Add inline wikilinks both directions, update MOC membership. The primitive that turns isolated notes into a graph.