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 PedroMosquera/squadai --skill writing-plansgit clone --depth 1 https://github.com/PedroMosquera/squadaiWrote 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/pedromosquera/squadai/writing-plans)<a href="https://agentmods.dev/skills/pedromosquera/squadai/writing-plans"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/writing-plans/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pedromosquera/squadai/writing-plans"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00014 | $0.00528 |
| Opus 5 | $0.00007 | $0.00264 |
| Sonnet 5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
writing-plans 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 10d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans Skill
Convert a list of test scenarios into an ordered implementation plan. This skill is used by the Planner after the Brainstormer produces scenarios.
Steps
-
Review scenarios: Read the brainstorming output carefully.
- Identify all test scenarios that need coverage
- Note dependencies between scenarios (some tests require others to pass first)
- Identify which scenarios share setup/teardown
-
Group into test suites: Organize scenarios by the code unit they test.
- Group tests for the same function/method together
- Identify shared fixtures that should be extracted
- Note where table-driven tests are appropriate (multiple inputs → same function)
-
Order the tests: Sequence tests from simplest to most complex.
- Start with happy path tests (positive cases)
- Follow with edge cases
- End with error scenarios
- Ensure each test builds on knowledge from previous tests
-
Write the test plan: For each test, specify:
- Test name (format:
TestFunctionName_Scenario_ExpectedResult) - Setup required (fixtures, mocks, temp dirs)
- The specific action to invoke
- The assertion to make (exact values, not just "no error")
- Teardown needed (if any)
- Test name (format:
-
Identify implementation dependencies: List what code must be written.
- New functions or methods needed
- Interface changes required
- New types or structs
- Dependency injection points for testability
-
Estimate complexity: Flag high-effort items.
- Simple (< 30 min): straightforward logic, no external dependencies
- Medium (30 min – 2 hrs): requires new abstraction or refactoring
- Complex (> 2 hrs): involves multiple components or tricky concurrency
Output Format
## Test Plan
### Suite: <FunctionName>
- [ ] Test: TestFunctionName_HappyPath_ReturnsResult
Setup: <what to prepare>
Action: call FunctionName with <inputs>
Assert: result equals <expected>
- [ ] Test: TestFunctionName_EmptyInput_ReturnsError
...
## Implementation Dependencies
1. <what needs to be implemented>
2. ...
## Complexity Estimates
- TestFunctionName_HappyPath: Simple
- ...
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.
- 10d ago First seen · 72 lines · 14 tokens per session scan A a87ec294f1ad
writing-plans is a skill published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 528 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
ijfw-tdd
RED-GREEN-REFACTOR enforcement. Use when implementing a feature or bugfix before writing implementation code. Trigger: tdd, test first, red green refactor, /ijfw-tdd.
tdd-cycle
Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".
red-green-refactor
Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like…
atomic-tdd
Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…