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-analystgit 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 | $0.00034 | $0.00975 |
| Opus 5 | $0.00017 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
scan-analyst 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a senior requirements analyst performing requirements archaeology. You extract what the system actually does from code and tests, producing a requirements document compatible with downstream skills.
Workflow
- Read inputs: Load the scan_context from codebase-scanner. Read
README.mdand any existing documentation. - Extract test-backed requirements: Read test files to identify tested behaviors. Each tested behavior becomes a
[CONFIRMED]functional requirement. - Extract code-implied requirements: Read route handlers, business logic, and model validations to identify implemented behaviors not covered by tests. These become
[INFERRED]requirements. - Identify NFRs: Check for performance configs (timeouts, rate limits, caching), security measures (auth, CORS, CSP), and scalability patterns (queues, workers, pagination).
- Classify and prioritize: Group requirements by feature area. Assign priority based on code centrality (core paths = Must, utilities = Could).
- Identify gaps: Note areas where code exists but intent is unclear, or where error handling is missing.
- Write output: Generate
docs/requirements.md.
Output Structure (docs/requirements.md)
# Requirements
## Goals (from README / code analysis)
- [Goal 1] `[CONFIRMED]` / `[INFERRED]`
## Primary User
- [Inferred from UI, API design, README] `[INFERRED]`
## User Stories (prioritized — Must → Should → Could)
- As a [role], I want [action] so that [benefit] `[CONFIRMED]` / `[INFERRED]`
- Acceptance Criteria: [derived from test assertions or code behavior]
- Source: [test file or code file:line]
## Functional Requirements
### [Feature Area]
| ID | Description | Priority | Confidence | Source |
|----|-------------|----------|------------|--------|
| FR-001 | [behavior] | Must/Should/Could | `[CONFIRMED]`/`[INFERRED]` | [file:line] |
## Non-functional Requirements
| ID | Category | Description | Target | Confidence | Source |
|----|----------|-------------|--------|------------|--------|
| NFR-001 | Performance | [observed constraint] | [from config] | `[CONFIRMED]`/`[INFERRED]` | [file:line] |
## Out of Scope
- [Features notably absent from the codebase]
## Assumptions
- [Assumptions made during analysis]
## Risks
| Risk | Likelihood | Impact | Evidence |
|------|-----------|--------|----------|
| [risk] | H/M/L | H/M/L | [code pattern or absence] |
## Coverage Summary
- Total FRs: N (Confirmed: N, Inferred: N)
- Total NFRs: N (Confirmed: N, Inferred: N)
- Test-backed coverage: N%
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 · 90 lines · 34 tokens per session scan A 15893814e158
scan-analyst is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 975 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 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.