Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add egorfedorov/claude-context-optimizer/plugin install 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-coach)<a href="https://agentmods.dev/skills/egorfedorov/claude-context-optimizer/cco-coach"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/cco-coach/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/egorfedorov/claude-context-optimizer/cco-coach"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/cco-coach.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 | $0.00031 | $0.00415 |
| Opus 5 | $0.00015 | $0.00208 |
| Sonnet 5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
cco-coach 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 10d 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.
What it actually says
Prompt Coach
When the user runs /cco-coach or asks for "prompt feedback" / "оцени мой промпт", run the analyzer on the user's last natural-language ask (or on text they provide).
How to use
If the user passes text after the command (e.g. /cco-coach add login screen):
node ${CLAUDE_PLUGIN_ROOT}/src/prompt-coach.js analyze "the prompt text here"
If no text given, show recent prompt history and average score:
node ${CLAUDE_PLUGIN_ROOT}/src/prompt-coach.js history 10
What the score means
The coach grades on four dimensions (S/A/B/C/D/F):
- Specificity — does the prompt name files, line numbers, identifiers?
- Scope — is the change bounded? "fix bug in src/auth.js:42" beats "fix all bugs"
- Success criteria — how do we know it's done? (tests pass, error gone, etc.)
- Length — too short usually means under-specified; too long buries the ask
Presentation
After running the script, summarise the top 1–3 suggestions in plain language and offer to rewrite the prompt for the user. If they say yes:
node ${CLAUDE_PLUGIN_ROOT}/src/prompt-coach.js improve "the original prompt"
Then show the improved version with a brief diff explaining what changed.
When to suggest this proactively
If you notice the user's prompt scored ≤60 in the last UserPromptSubmit hook and a task is going off the rails (lots of reads with no edits), gently suggest /cco-coach to refine.
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.
- 10d ago First seen · 45 lines · 31 tokens per session scan A 4892abda7f5d
cco-coach is a skill published in the GitHub repository egorfedorov/claude-context-optimizer (107 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 415 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:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
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:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
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…