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/ruizrica/toolkit/agent-plangit clone --depth 1 https://github.com/ruizrica/toolkitWhat 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 | $0.01583 |
| Opus 5 | $0.00000 | $0.00792 |
| Sonnet 5 | $0.00000 | $0.00317 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
agent-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 3d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agent-plan
Interactive single-document plan workflow. Gathers the full shape of a plan via AskUserQuestion, writes a maximally robust markdown plan, gates on agent-viewer plan approval, then executes in the same session and closes the loop with an auto-generated completion report.
Sister command to /agent-spec, which is the multi-document (requirements/design/tasks) equivalent. Use /agent-plan when the work is a single coherent change; use /agent-spec when the feature needs requirements/design/tasks separation.
Usage
/agent-plan [plan topic] [--name NAME] [--agent inline|haiku|sonnet|opus]
Arguments
| Argument | Required | Description |
|---|---|---|
| plan topic | Yes | Plain-language description of the work |
| --name NAME | No | Plan name (defaults to YYYY-MM-DD-<slug>) |
| --agent inline|haiku|sonnet|opus | No | Execution mode (default: inline) |
Workflow Phases
The command runs 5 phases end-to-end:
Phase 1 — Context
Spawns one Haiku scout agent that scans the repo for:
- Files/modules/functions relevant to the topic
- Existing patterns, conventions, test styles
- In-progress changes that might conflict
Lightweight by design — plans are single-document and smaller than specs, so one agent is enough.
Phase 2 — Interactive Q&A
Groups of 2–4 questions per AskUserQuestion call, covering:
| Group | Questions |
|---|---|
| Goal & Scope | problem, success criterion, in/out-of-scope |
| Constraints & Approach | technical/time/stakeholder constraints, preferred strategy, things to avoid |
| Staging & Risks | natural breakpoints, failure modes, rollback, external dependencies |
| Verification | test plan, acceptance gate |
All Q&A is appended to .context/plans/<plan_name>.qa.md (audit trail).
Phase 3 — Assemble
Writes the plan to .context/plans/<plan_name>.md with every section the viewer renders — Context, Goal, Scope, Approach (with Mermaid), per-Phase task checklists with Files-touched lists, Risks table, Verification Plan, Rollback, Open Questions. Sections that don't apply are written as N/A — reason rather than omitted.
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.
- 3d ago First seen · 154 lines · 0 tokens per session scan A 40444d179748
agent-plan is a command published in the GitHub repository ruizrica/toolkit (5 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,583 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.
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.