Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/avelikiy/great_ctonpx agentmods add commands/avelikiy/great_cto/ccrWrote 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/commands/avelikiy/great_cto/ccr)<a href="https://agentmods.dev/commands/avelikiy/great_cto/ccr"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/ccr/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/commands/avelikiy/great_cto/ccr"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/ccr.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 | $0.00036 | $0.00602 |
| Opus 5 | $0.00018 | $0.00301 |
| Sonnet 5 | $0.00007 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
ccr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are the great_cto /ccr command — the retrieval half of CCR (Compressed Context
with Retrieval). great_cto compresses context aggressively (memory-filter,
importance-trim, log/json compressors) but never deletes the original — it stores it
locally under .great_cto/ccr/. When you realise you need something that was filtered
out, /ccr <id> brings the full original back. This is the safety net that lets great_cto
compress hard without losing answers.
Step 1 — Parse argument
ID="${ARGUMENTS%% *}"
- Empty
$ID→ list mode. - Otherwise → recall mode.
Step 2 — List recoverable items (no id)
node scripts/lib/ccr.mjs list --limit 20
Rows: id bytes source preview. source is who stored it (memory-filter = dropped
lessons/decisions, compress = trimmed logs/tool output, …).
Step 3 — Recall the original (id given)
node scripts/lib/ccr.mjs recall "$ID"
- Prints the full uncompressed original — feed it back into your reasoning.
- Exit 1 if the id is unknown (it may have been pruned — CCR keeps the most recent ~500
items per project). Try
/ccr(list) to see what's still available.
Where ids come from
Compression components append a footer when they drop something:
<!-- ccr: 2 item(s) elided but recoverable. Run `/ccr <id>`:
- `a1b2c3d4e5f6` — ## Lesson: rate-limit Stripe webhooks
- `0f9e8d7c6b5a` — ## Decision: pin model versions in ADR-LLM
-->
If an elided item looks relevant to the task, /ccr it instead of guessing.
Notes
- Project-local (
.great_cto/ccr/); content-addressed (identical content → one id, auto-dedup). - Not the same as
/recall(which searches session history by keyword) —/ccrretrieves a specific compressed-out artifact by id.
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 · 63 lines · 36 tokens per session scan A 12638e690705
ccr is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 602 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 2026-09-03.
Other commands, from other repositories
rust-teach
One-time setup that scans your Rust project, understands its patterns and conventions, and writes a Rust-specific context section to your CLAUDE.md. Run once per project to establish persistent Rust guidelines.
fec-review
Conduct a standardized review of the specified file or recently changed front-end code, output a graded review report and save it as a Markdown file.
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.
develop
Implement skill development issues with TDD-governed workflow.
fec-doc-sync
Sync README, docs, environment variables, scripts, API/routing/component descriptions and deployment instructions from code and project sources of truth.
rust-critique
Deep code critique — read the target Rust code and apply the full review process. Evaluates soundness, ownership, error handling, type design, async correctness, performance, and architecture. Think like a senior Rust engineer giving honest feedback.