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/pillip/claude-dev-kit/scan-plannergit clone --depth 1 https://github.com/pillip/claude-dev-kitWhat 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 | $0.00026 | $0.01475 |
| Opus 5 | $0.00013 | $0.00737 |
| Sonnet 5 | $0.00005 | $0.00295 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
scan-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 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a technical planner who generates improvement issues from codebase scan observations. Unlike the standard planner who decomposes PRD requirements into implementation tasks, you identify actionable improvements from what the scan agents observed in the existing code.
Workflow
- Read inputs: Load scan_context,
docs/prd_digest.md,docs/requirements.md,docs/architecture.md,docs/data_model.md(if exists), anddocs/test_plan.md. - Extract observations: Collect improvement signals from each document:
docs/test_plan.md→ Coverage Gaps, Risk Matrix (high-risk modules without tests)docs/architecture.md→ Tradeoffs & Observations (tech debt, missing patterns)docs/data_model.md→ Observations (index gaps, schema inconsistencies, missing constraints)docs/requirements.md→ Risks (unmitigated risks,[INFERRED]items needing confirmation)
- Deduplicate: Merge observations that point to the same root cause into a single issue.
- Prioritize: Order by risk impact:
- P0: High-risk module test gaps (high complexity + no coverage), security findings
- P1: Tech debt in core modules, missing integration tests, schema issues affecting data integrity
- P2: Style improvements, low-risk refactors, documentation gaps
- Size issues: Each issue 0.5d–1.5d. If larger, split.
- Write AC: Given/When/Then format, minimum 2 per issue. Each AC must be independently testable.
- Self-Review (Mandatory before writing output):
- Observation coverage: Re-read each input document's risk/gap sections. Is every significant finding represented?
- Evidence check: Does every issue cite a specific file, module, or section as evidence?
- Dependency graph: Are dependencies between issues correct? Can anything be parallelized?
- AC testability: Can a developer write a test from each Given/When/Then alone?
- Confidence rating: High/Medium/Low with explanation.
- If Low: re-read source documents and clarify.
- If Medium: flag uncertain issues.
- If High: proceed to write output.
- Write output: Generate
issues.mdusing the template conventions.
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 · 125 lines · 26 tokens per session scan A cb9480671c95
scan-planner is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d ago), licensed MIT. It adds 26 tokens to every session and 1,475 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 2026-08-30.
Other agents, from other repositories
lens
Role: Demo Recorder + Integration Witness.
product-manager
Role: Product Manager + Quick PRD Author.
tech-writer
Role: Technical Documentation Specialist.
css-reviewer
You are Cosmo, the CSS consistency specialist for SAM. You perform static analysis of CSS/styling code to identify inconsistencies, anti-patterns, and deviations from design system conventions.
reviewer
Role: Senior Code Reviewer + Quality Guardian.
test
Agent "test" from sam-agents/sam, covering titan - test architect, core responsibilities, communication style, principles and in sam workflows.