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/jayminwest/canopy/prioritizegit clone --depth 1 https://github.com/jayminwest/canopyWhat 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 | $0.00002 | $0.01113 |
| Opus 5 | $0.00001 | $0.00557 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
prioritize 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.
This is a copy
89% identical to prioritize — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description
Analyze all open issues across GitHub Issues and Seeds, cross-reference with codebase health, and recommend the top ~5 issues to tackle next.
Argument: $ARGUMENTS — optional: a label or area to focus on (e.g., cli, storage, emit). If empty, analyze everything.
gather-issues
Use the Task tool to spawn three parallel agents:
Agent A: GitHub Issues
- Run
gh issue list --state open --limit 50 --json number,title,author,labels,createdAt,updatedAt,body - For each issue, capture: number, title, labels, author, creation date, body summary
- Note any issues with community engagement (comments, thumbs-up, external authors)
Agent B: Seeds Issues
- Run
sd listandsd ready - For each open issue, run
sd show <id>to get full details - Capture: id, title, type, priority, status, description, dependencies/blockers
- Build a dependency graph: which issues block which
Agent C: Codebase Health
- Run
bun testand capture pass/fail counts - Run
bun run lintand capture error counts - Run
bun run typecheckand capture error counts - Search for
TODO,FIXME,HACKcomments and count them - Check which source files lack test coverage (compare
src/**/*.tsvssrc/**/*.test.ts) - Summarize: is the codebase healthy, or are there quality issues that need attention
cross-reference
After all three agents complete:
- Deduplicate: Match GitHub issues to Seeds issues that describe the same work (same title, overlapping description, related files)
- Dependency mapping: Identify chains — issues that must be done before others can start
- Cluster detection: Group related issues that could be tackled together (same subsystem, same theme, same files)
- Staleness check: Flag issues that have been open a long time with no activity
scoring
For every unique issue (deduplicated), assess:
a. Impact
- Does it fix a bug that blocks users?
- Does it enable new capabilities or unblock other work?
- How many other issues does it unblock (dependency graph)?
- Does it affect external users (GitHub issues from community)?
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 · 115 lines · 2 tokens per session scan A f07e88ad1b36
prioritize is a command published in the GitHub repository jayminwest/canopy (39 stars, last pushed 29d ago), licensed MIT. It adds 2 tokens to every session and 1,113 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to prioritize, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.