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 commands/chappygo-os/atomic-spec/cleanupgit clone --depth 1 https://github.com/Chappygo-OS/Atomic-SpecWhat 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 | $0.00017 | $0.06250 |
| Opus 5 | $0.00009 | $0.03125 |
| Sonnet 5 | $0.00003 | $0.01250 |
| Haiku 4.5 | $0.00002 | $0.00625 |
Grade A, and why
cleanup 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 3d 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 — 846 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Purpose
This command identifies orphaned/unused code across the codebase and helps safely remove it. It adapts to the project's tech stack and gives the user full control over detection methods and cleanup actions.
⚠️ CRITICAL PRINCIPLES
- Report first, delete later - NEVER auto-delete. Always show findings, get user approval.
- Per-domain control - User chooses approach for each domain (frontend, backend, database) independently.
- Adapt to what exists - Only offer cleanup for domains that actually exist in the project.
- External tools are optional - User can always choose AI-based detection instead.
Phase 1: Project Analysis
1.0 Load Project Defaults Registry
Per Constitution Article IX, Directive 7 - Load registry first.
Read specs/_defaults/registry.yaml to get authoritative tech stack information:
-
Extract tech stack from registry:
architecture.pattern,architecture.layers- System structurecode_patterns.data_access- Expected data access patternsbackend.language,backend.framework,backend.ormfrontend.framework,frontend.ui_librarydatabase.type,database.query_style
-
Registry provides ground truth for what technologies SHOULD be in use. If cleanup finds code using technologies NOT in registry, flag as potential orphan.
1.1 Detect Project Structure
Read plan.md from the current feature directory (or project root) to extract tech stack.
Also cross-reference with specs/_defaults/registry.yaml for authoritative defaults.
Determine which domains exist:
┌─────────────────────────────────────────────────────────────┐
│ Domain Detection │
├─────────────────────────────────────────────────────────────┤
│ │
│ FRONTEND exists if ANY of: │
│ ├── frontend/ directory exists │
│ ├── src/components/ exists │
│ ├── package.json has react/vue/angular/svelte │
│ └── plan.md mentions frontend framework │
│ │
│ BACKEND exists if ANY of: │
│ ├── backend/ directory exists │
│ ├── app/ or src/ with routes/api folders │
│ ├── requirements.txt / pyproject.toml / go.mod │
│ └── plan.md mentions backend framework │
│ │
│ DATABASE exists if ANY of: │
│ ├── migrations/ directory exists │
│ ├── prisma/ or drizzle/ or alembic/ directories │
│ ├── models/ with ORM definitions │
│ └── plan.md mentions database/ORM │
│ │
└─────────────────────────────────────────────────────────────┘
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.
- 3d ago First seen · 846 lines · 17 tokens per session scan A 256b6db9302b
cleanup is a command published in the GitHub repository Chappygo-OS/Atomic-Spec (10 stars, last pushed 10d ago), licensed MIT. It adds 17 tokens to every session and 6,250 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 commands, from other repositories
data-modeling
Design and implement data models (schemas, ERD, data warehouse).
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
ijfw
IJFW command index. Groups commands by intent: Build / Remember / Ship / Review / Configure.
core-review
Review code changes against SpecOps project-specific patterns. Catches recurring failure modes from real PRs — tool abstraction violations, generated file drift, cross-platform gaps, variable inconsistencies, and more. Complements full-review-gate (generic quality) and pr-fix (applying bot comments).
full-review-gate
Perform a comprehensive repository code review in an isolated worktree. Fix P0/P1 findings and ship them as a PR targeting the current branch.
ship-pr
Commit all changes to a new branch, push, and open a PR for review. The original branch stays clean.