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.
git clone --depth 1 https://github.com/codeready-toolchain/tarsyWrote 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/codeready-toolchain/tarsy/learn)<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/learn"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/learn/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/codeready-toolchain/tarsy/learn"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/learn.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 | $0.00015 | $0.00146 |
| Opus 5.5 | $0.00006 | $0.00058 |
| Sonnet 5.5 | $0.00003 | $0.00029 |
| Haiku 4.5 | $0.00002 | $0.00015 |
Grade A, and why
learn 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.
What it actually says
Analyze this session and extract non-obvious learnings into AGENTS.md files.
AGENTS.md can exist at any directory level. Prefer the nearest package/feature directory over the repo root.
Include only:
- Hidden relationships between modules
- Surprising execution paths
- Non-obvious env/config
- Debugging breakthroughs
- Build/test commands missing from docs
- Files that must change together
Do not include obvious docs facts, standard language behavior, or session chatter.
Process: review session → choose scope → read existing AGENTS.md → append 1–3 line bullets → summarize what changed.
$ARGUMENTS
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 · 23 lines · 15 tokens per session scan A 0b1fbb61853e
learn is a command published in the GitHub repository codeready-toolchain/tarsy (10 stars, last pushed 5d ago), licensed Apache-2.0. It adds 15 tokens to every session and 146 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 commands, from other repositories
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.
speckit.superspec.brainstorm
../../.opencode/commands/speckit.superspec.brainstorm.md.
visualize
Open the local PI decision visualizer. Start the visualizer server backed by /.pi/decisions data, and open the result in the browser unless --no-open is passed.
sync-coordinator
Multi-package synchronization and version alignment with ruv-swarm coordination for seamless integration between claude-code-flow and ruv-swarm packages.