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/zebbern/agent-collab/setgit clone --depth 1 https://github.com/zebbern/agent-collabWhat 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 | $0.00011 | $0.00329 |
| Opus 5 | $0.00005 | $0.00164 |
| Sonnet 5 | $0.00002 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
set scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Create or update a goal file for this project.
- Interview briefly if needed: the goal statement, acceptance criteria
(mechanically checkable commands where possible,
manualotherwise), a ranked backlog of increments (each[a-z0-9-]+id, title, detail), andbudget.perStepDelegations(default 2). - Draft the goal JSON (schemaVersion 1) to a temp file.
- Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/goal-companion.mjs" set --file <temp-path>The companion validates and writes.claude/goals/<slug>.json; if it refuses, fix exactly what it names and re-run — never bypass validation. Renaming a slug:setwrites the new file and never deletes the old one — remove.claude/goals/<old-slug>.jsonyourself, orstatus/nextwill refuse listing both. - Show the result of
node "${CLAUDE_PLUGIN_ROOT}/scripts/goal-companion.mjs" status <slug>. - Remind the user the goal file is git-tracked project content: commit it.
Trust note: check runs command criteria via the shell — the same trust
level as npm scripts. Review goal files in untrusted repos before running.
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.
- 2d ago First seen · 26 lines · 11 tokens per session scan A ae1dd0bb1672
set is a command published in the GitHub repository zebbern/agent-collab (32 stars, last pushed 17d ago), licensed Apache-2.0. It adds 11 tokens to every session and 329 once invoked, about $0.0001 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 commands, from other repositories
grow-a-product
Workflow recipe — turn a growth goal into a funnel diagnosis, experiment backlog, retention loop, and lifecycle journeys by chaining 4 skills.
plan-sprint
Run a design sprint end to end — challenge framing, schedule, exercises, and prototype test plan.
learn
Learn about Task Master capabilities through interactive exploration.
sync-readme
Export tasks to README.md with professional formatting.
analyze-project
Advanced project analysis with actionable insights and recommendations.
to-pending
Command "to-pending" from WYRE-AI/autotask-mcp, covering setting task to pending, execution, validation and smart actions.