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/justifi-tech/web-component-library/plangit clone --depth 1 https://github.com/justifi-tech/web-component-libraryWhat 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 | $0.00514 |
| Opus 5 | $0.00000 | $0.00257 |
| Sonnet 5 | $0.00000 | $0.00103 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
plan 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.
How it starts
The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
- Study AGENTS.md for guidelines.
- Study specs/README.md to understand existing specs and their statuses. Check if a spec already covers what the user is asking for before creating a new one.
- Do NOT read specd_history.md in full — it can be very large. Grep for the spec name to find relevant entries and avoid duplicating completed work.
- We are going to work on modifying and creating new specs.
- We do not write code unless explicitly asked to do so. We only modify *.md files and specd_work_list.md.
- When doing research use "model: Sonnet" agents in parallel to get the information that you need.
Workflow
- Discuss — Ask clarifying questions about what the user wants. Understand scope, edge cases, and design decisions before writing anything.
- Write the spec — Create or update the spec in
specs/. Follow the format inspecs/example-spec.md. Specs define WHAT and WHY, not HOW. New specs start at v0.1 with status Draft. - Write work items as you go — As spec sections solidify, write corresponding work items to
specd_work_list.mdunder a## spec-name vX.Ysection header. Don't wait until the end — writing items incrementally lets the user see what the loop will do and course-correct early. Each item should be completable in a single agent iteration. Add(blocked: reason)for items that depend on other items. - Update specs/README.md — Add or update the spec entry in the index table with the correct version and status.
- Remind the user — The spec starts as Draft. When the user is satisfied, they change the status to Ready in both the spec file and specs/README.md. The loop only implements Ready specs.
When updating an existing spec, always review the work items in specd_work_list.md for that spec. Remove items that are no longer relevant, update items that changed, and add new items for new requirements.
The work items in specd_work_list.md are what the loop uses to know what to implement. If you don't write them, the loop has nothing to do.
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 · 25 lines · 0 tokens per session scan A 449bac2f1ee8
plan is a command published in the GitHub repository justifi-tech/web-component-library (5 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 514 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
git
Git operations with intelligent commit messages and workflow optimization.
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.