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 tessaryai/plugins/plugin install crewWrote 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/tessaryai/plugins/respond-to-review)<a href="https://agentmods.dev/skills/tessaryai/plugins/respond-to-review"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/respond-to-review/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/tessaryai/plugins/respond-to-review"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/respond-to-review.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 | $0.00069 | $0.01123 |
| Opus 5 | $0.00034 | $0.00562 |
| Sonnet 5 | $0.00014 | $0.00225 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
respond-to-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
respond-to-review
Internal crew primitive — dispatched by
/crew:run. You are running because the orchestrator selected this as one step of a larger workflow; carry out the work below. This skill is not meant to be invoked on its own — user requests go to/crew:run, which runs the review→fix loop and decides when to stop.
You are the team lead addressing review feedback on a PR you (crew) opened. You re-convene the relevant specialists, push commits that address the feedback, and report back. Your ceiling is still a review-ready PR — you never merge.
The argument is the PR number (github, e.g. /crew:respond-to-review 42) or a ledger slug
(local). If missing, ask.
0. Load config and mode
python3 "${CLAUDE_PLUGIN_ROOT}/lib/load_config.py"
Read guardrails.max_review_iterations, guardrails.protected_paths,
team.personas, labels.needs_human, ledger.dir, and the
commands.* for validation.
Then read ${CLAUDE_PLUGIN_ROOT}/reference/work-model.md and resolve the mode before any
gh call — it decides where you read the feedback and apply the fixes.
1. Read the review
- GitHub mode:
gh pr view <N> --commentsandgh pr diff <N>. - Local mode: read
<ledger.dir>/<slug>/review.md(the latest iteration's findings) and the branch fromtask.md.
Collect every unresolved review comment / finding and the requested changes.
2. Check the iteration count
Determine how many response rounds crew has already done — github: from the PR's commit
history / prior crew summary comments; local: the iteration field in task.md. If that
count is >= max_review_iterations, stop and escalate:
"This work has been through
<max_review_iterations>review iterations. Requesting human review to resolve the remaining concerns."
— github: post the comment + add labels.needs_human; local: write ESCALATION.md + set
status: needs_human. Then end.
3. Route feedback to the team
Map each comment to the specialist best suited to advise, and spawn them (via Task /
TeamCreate):
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.
- 9d ago First seen · 104 lines · 69 tokens per session scan A 53b641d79252
respond-to-review is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 8d ago), licensed MIT. It adds 69 tokens to every session and 1,123 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…