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/egorfedorov/claude-context-optimizer/cco-patternsnpx skills add egorfedorov/claude-context-optimizer --skill cco-patternsgit clone --depth 1 https://github.com/egorfedorov/claude-context-optimizerWrote 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/egorfedorov/claude-context-optimizer/cco-patterns)<a href="https://agentmods.dev/skills/egorfedorov/claude-context-optimizer/cco-patterns"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/cco-patterns.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 | $0.00039 | $0.00576 |
| Opus 5 | $0.00019 | $0.00288 |
| Sonnet 5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
cco-patterns 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCO Patterns — share what the project has learned
Patterns are learned per-machine, per-project: which files are usually waste, which are usually useful, which get edited together. A teammate's fresh clone starts blind and re-learns the same lessons by wasting the same tokens.
This makes them portable. Run from the plugin root (the directory containing
src/patterns-share.js).
Parse $ARGUMENTS:
export
node src/patterns-share.js export
Writes .cco/patterns.digest.json in the project (override with --out).
The digest contains relative paths and counts only — no file contents, no absolute paths, no home directory. Entries that can't be expressed relative to the project root are dropped, and the command reports how many. The file is audited before writing; if anything identifying slipped in, it refuses to write rather than produce a file someone might commit.
Tell the user the digest is safe to commit, and that committing it is the point: teammates get it on clone.
import <file>
node src/patterns-share.js import .cco/patterns.digest.json
Merges into the current project's patterns. Imported data is stored as a separate prior — it never touches the user's own counts.
This matters and is worth saying out loud: confidence is computed from how
many sessions this machine observed a file in. Folding someone else's
sessions into that number would make the user's own confidence a lie. So the
import fills in only where the user has no observations of their own — the
fresh-clone case — and local evidence always wins.
The digest is audited on the way in too, since it came from elsewhere. A file with absolute paths or traversal segments is rejected, not sanitized.
show
node src/patterns-share.js show
Lists what was imported for this project and how each file is labelled.
Suggesting this
Worth offering when:
- The user is setting up a repo for a team and asks about onboarding cost.
- A project has meaningful waste history (
/cco-shieldshows repeat offenders) that every teammate will otherwise rediscover. - Someone just cloned a repo that already has
.cco/patterns.digest.json— offer to import it.
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.
- 5d ago First seen · 71 lines · 39 tokens per session scan A 15014584ab68
cco-patterns is a skill published in the GitHub repository egorfedorov/claude-context-optimizer (104 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 576 once invoked, about $0.0002 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
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
alive:my-context-graph
Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.