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 commands/codeready-toolchain/tarsy/pr-commentgit clone --depth 1 https://github.com/codeready-toolchain/tarsyWhat 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 | $0.00000 | $0.01568 |
| Opus 5 | $0.00000 | $0.00784 |
| Sonnet 5 | $0.00000 | $0.00314 |
| Haiku 4.5 | $0.00000 | $0.00157 |
Grade A, and why
pr-comment 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 3d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Review Comment - Context
The user's message contains a Pull Request review comment that needs to be addressed.
Treat the user's input as the reviewer's feedback. Your job is to decide whether to Implement, Skip, Clarify, or Alternative — not to make the review green by default.
How to Address the PR Comment
Follow this systematic approach:
1. Identify the Context
First, determine what code the comment refers to:
- Read the files mentioned or implied by the comment
- Use recently viewed files, or file context to identify relevant files
- Understand the current implementation before proceeding
- Check how sibling code handles the same concern (other tools, callers, established patterns in this repo). Inconsistency is a signal the suggestion may be over-scoped.
2. Analysis Phase
Do not blindly implement the suggestion. Analyze before writing code.
Soundness vs necessity
A comment can be technically correct and still not worth doing. Judge both:
| Question | Ask |
|---|---|
| Sound? | Is the finding still true against current code? Is the reviewer mistaken or missing context? |
| Necessary? | What concrete scenario does this prevent or improve? How likely is it here? |
| Proportionate? | Does the added complexity/cost match the realistic risk or benefit? |
| Consistent? | Do peer paths (similar tools/APIs) already accept the same tradeoff? |
"Still valid" means still true in the code — not "must implement." Valid but unnecessary nits (theoretical TOCTOU, speculative caching, style-only refactors with large blast radius) should use Skip (disagreement is a common rationale) unless the user explicitly wants them.
Before implementing security, concurrency, or perf nits
State in your reasoning (and to the user if you will change code):
- Scenario — the relevant concrete case: failure mode, abuse path, or performance impact (actors, timing/preconditions, and what goes wrong)
- Likelihood — why it would or would not happen in this product/path
- Decision — exactly one of: Implement / Skip / Clarify / Alternative
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.
- 3d ago First seen · 170 lines · 0 tokens per session scan A 8aee0b8baa81
pr-comment is a command published in the GitHub repository codeready-toolchain/tarsy (10 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,568 tokens. 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
multi-agent-optimize
The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated agent-based optimization. Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach to performance engineering across multiple…
update-changelog-and-tag
You are preparing a release. Follow these steps precisely.
end-session
Wrap up the work session with read-only evidence gathering, owner-classified documentation handoffs, gated issue sync, Kano refinement, and git hygiene checks.
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.
research_web
Conduct extensive web research on technical topics with validated references.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".