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 skills add jayminwest/canopy --skill canopy-prompt-workflowgit clone --depth 1 https://github.com/jayminwest/canopyWrote 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/jayminwest/canopy/canopy-prompt-workflow)<a href="https://agentmods.dev/skills/jayminwest/canopy/canopy-prompt-workflow"><img src="https://agentmods.dev/badge/skills/jayminwest/canopy/canopy-prompt-workflow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01554 |
| Opus 5 | $0.00021 | $0.00777 |
| Sonnet 5 | $0.00008 | $0.00311 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
canopy-prompt-workflow 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 8d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
canopy-prompt-workflow
Use this skill when you are an agent working inside the canopy repo and
you need to compose a new prompt by inheritance, then emit the
rendered result to disk. It encodes the canonical prompt-authoring
loop documented in SPEC.md so an agent can do it from a cold start
without re-reading the full design record.
Pre-flight
The repo must already be initialised. Verify:
ls .canopy/ # config.yaml + prompts.jsonl + schemas.jsonl
bunx cn doctor # exits 0 when the store is healthy
If .canopy/ is missing, run bunx cn init first. If cn doctor
reports problems, fix them (or escalate) before continuing — never
hand-edit .canopy/prompts.jsonl to "fix" things; use cn commands so
locks + atomic writes are honoured.
Procedure
1. Decide the prompt's shape
A canopy prompt is a JSONL record with named sections. Before touching the CLI, write down:
- The prompt's stable
name(kebab-case, must be unique in the store). - Its parent (the
extends:target), if it inherits. Pick the most specific base whose sections you want to inherit. - The minimum set of
sections(name,body, optionalrequired) the new prompt adds or overrides. Inheriting sections is preferred over duplicating them — that is the whole point of canopy. - The
schemait should validate against, if any (see.canopy/schemas.jsonl).
2. Inspect existing prompts
bun run src/index.ts list # lists all prompts
bun run src/index.ts show <parent-name> # see the parent's sections
bun run src/index.ts tree <parent-name> # full inheritance tree
If a sibling prompt already does most of what you want, extend it instead of forking — every duplicated section is one more place a future edit will drift.
3. Create or update the prompt
To create a new prompt by inheritance:
bun run src/index.ts create \
--name <prompt-name> \
--extends <parent-name> \
--section role:"You are ..." \
--section constraints:"- Never push to canonical branch"
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.
- 8d ago First seen · 167 lines · 42 tokens per session scan A 6bdaec9fa5e2
canopy-prompt-workflow is a skill published in the GitHub repository jayminwest/canopy (40 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,554 once invoked, about $0.0002 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 skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…