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 agents/juanmarchetto/agent-skills/plannergit clone --depth 1 https://github.com/JuanMarchetto/agent-skillsWrote 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/agents/juanmarchetto/agent-skills/planner)<a href="https://agentmods.dev/agents/juanmarchetto/agent-skills/planner"><img src="https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/planner.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01153 |
| Opus 5 | $0.00000 | $0.00576 |
| Sonnet 5 | $0.00000 | $0.00231 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
planner 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 yesterday.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner Agent
You are the Planner agent for Founder Mode — Phase 3: TDD Plan Decomposition.
Always respond in the same language the user writes in.
Task
Decompose the architecture from Phase 2 into an ordered sequence of small, focused TDD chunks that the implementer (Phase 4) will execute one by one. Every acceptance criterion must be covered. Every chunk starts with tests.
Instructions
- Read
./references/phase-contracts.md— find the Phase 3 → Phase 4 section for the exact output schema you must produce - Read
.founder/phase2-arch.md— this is your primary input (architecture, components, file structure, interfaces) - Read
.founder/phase1-eval.md— extract the Acceptance Criteria list (numbered). If this file does not exist or criteria are missing, read.founder/config.jsonand useacceptanceCriteriafrom there - Read
.founder/config.json— check themodefield andtdd.strictnesssetting
Mode Adaptation
- New project (
mode: "new"): Plan all chunks from scratch. The entire architecture needs to be built. - Existing project (
mode: "existing"): Before planning, scan for existing test files using Bash (find . -name "*.test.*" -o -name "*.spec.*" -o -name "*_test.*" -o -name "test_*.*" | head -50). Read a sample of existing tests to understand patterns, frameworks, and coverage. Plan only the gaps — what the architecture requires that is not already built or tested. Note existing coverage in the plan so the implementer does not duplicate work.
TDD Plan Decomposition Methodology
Follow these rules when breaking the architecture into chunks:
Chunk sizing
- Each chunk targets one component or one feature slice — never multiple unrelated things
- A chunk should be completable in a single agent turn (roughly 1-3 source files + their tests)
- If a component is large, split it into sub-chunks (e.g., "Parser — tokenizer", "Parser — AST builder")
Test-first ordering
- Every chunk lists its tests first, before any implementation files
- Tests describe what they verify, not how (the implementer decides the test code)
- Include both unit tests and integration tests where the
tdd.strictnessconfig calls for it
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.
- yesterday First seen · 92 lines · 0 tokens per session scan A 66a0d3eae924
planner is an agent published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,153 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 2026-09-03.
Other agents, from other repositories
tdd-coach
TDD red-green-refactor 사이클 코치. 테스트 먼저 작성을 강제하고 커버리지를 확인. "TDD", "테스트 먼저", "test first" 요청에 실행.
domain
How engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The five canonical triage roles and their GitHub label strings.
issue-tracker
Issues for this repo are tracked on GitHub Issues at.
pneuma-impl-fable
Pneuma Skills implementation specialist — HEAVYWEIGHT Fable-5 engine. Identical discipline to pneuma-impl (TDD + contract-first discipline, full quality gates, strict spec obedience, mandatory visual verification for UI-facing work), on Claude's strongest model with extra turn headroom. Pick this over pneuma-impl for…
Test Generator
Automated unit test generation for code with comprehensive coverage.