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 skills/andresharpe/dotbot/write-test-plannpx skills add andresharpe/dotbot --skill write-test-plangit clone --depth 1 https://github.com/andresharpe/dotbotWhat 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 | $0.00043 | $0.01562 |
| Opus 5 | $0.00022 | $0.00781 |
| Sonnet 5 | $0.00009 | $0.00312 |
| Haiku 4.5 | $0.00004 | $0.00156 |
Grade A, and why
write-test-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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Test Plan
Guide for producing a QA/UAT test plan that maps every acceptance criterion and feature scope item to verifiable test scenarios at the integration, acceptance, and exploratory levels.
Prerequisites
Both of these must exist before writing a test plan:
- Product specifications — at least one of:
mission.md,entity-model.md, PRD, change request, or interview summary - Task definitions — task list with acceptance criteria (via
task_list+task_getMCP calls, ortask-groups.json)
If either is missing, stop and surface the gap to the operator. A test plan written without full scope is incomplete by definition.
Inputs to Collect
.bot/workspace/product/mission.md # core goals and principles
.bot/workspace/product/entity-model.md # data model and relationships
.bot/workspace/product/tech-stack.md # runtime, frameworks, E2E tooling
.bot/workspace/product/task-groups.json # group-level scope and acceptance criteria
.bot/workspace/product/prd.md # if present
.bot/workspace/product/change-request-*.md # if present (for change-scoped plans)
task_list (MCP) # all tasks with names, categories, criteria
Read every relevant file first, then call task_list to pull the live task queue. Do not write the plan until all inputs are loaded.
Test Plan Structure
Output file: .bot/workspace/product/test-plan.md
Required Sections
1. Overview
- What this plan covers (product / feature / change request)
- Date and version
- Target audience: QA engineers, product owners, UAT participants
- Test approach summary
2. Scope
- In scope: features, workflows, integrations, and user-facing behaviours covered
- Out of scope: unit/component-level testing (covered by write-unit-tests), explicitly excluded areas
- Derive both lists directly from
mission.mdand task group scopes — nothing implied
3. Test Strategy
| Level | What is tested | Tooling | Who |
|---|---|---|---|
| Integration | Multi-component flows, API contracts, DB state | (from tech-stack.md) | QA |
| E2E / Acceptance | Full user journeys from UI to persistence | (from tech-stack.md) | QA |
| UAT | Business scenarios validated against real requirements | Manual | Product owner / stakeholders |
| Exploratory | Edge cases, UX, error recovery, accessibility | Manual | QA |
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 · 161 lines · 43 tokens per session scan A 77037497f423
write-test-plan is a skill published in the GitHub repository andresharpe/dotbot (54 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,562 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
hedgehog-planning-intake
Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…
inbound-triage
Maintainer-only. Use when triaging inbound GitHub issues and pull requests on skyf0xx/hedgehog — "triage the issues", "check the PRs", "review inbound", "what's in the queue". Reads each item read-only, judges it for security and for whether it is real, then fixes and closes or comments and closes. Not part of the…
bmad-product-brief
Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.
bmad-revendor
Maintainer-only. Use when re-vendoring vendor-skills/BMAD/ against a newer BMAD-METHOD commit — "update BMAD", "re-vendor BMAD", "bump the BMAD pin". Not part of the Hedgehog discipline a consuming project copies; this only applies to the Hedgehog repo itself.
bmad-deep-recon
Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here…
conventional-commits
Use when uncommitted changes need to be split into atomic, conventional commits ordered for review. Triggers on "commit this", "make commits", "clean up commits", "commit the changes". In Hedgehog, each Loop step is already meant to be its own commit — this skill matters most when a Correction Protocol fast-forward…