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/registrygit clone --depth 1 https://github.com/Chappygo-OS/Atomic-SpecWrote 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/commands/chappygo-os/atomic-spec/registry)<a href="https://agentmods.dev/commands/chappygo-os/atomic-spec/registry"><img src="https://agentmods.dev/badge/commands/chappygo-os/atomic-spec/registry.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 | $0.00058 | $0.04180 |
| Opus 5 | $0.00029 | $0.02090 |
| Sonnet 5 | $0.00012 | $0.00836 |
| Haiku 4.5 | $0.00006 | $0.00418 |
Grade A, and why
registry 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Honor the user input. Common patterns:
init(default when empty) — create or populate from scratchupdate— re-scan and surface new decisions against the existing registryaudit— read-only report of registry coverage vs. detected project signals
Outline
You are managing specs/_defaults/registry.yaml — the Project Defaults Registry defined by Constitution Article IX, Directive 7. This file is the single source of truth for project-wide technical decisions. Every command that generates code reads it on entry; every phase that makes new decisions writes to it on exit (with HITL approval).
Core guarantee: decisions are captured once, surface everywhere, never hallucinated on the fly.
This command covers the "On Entry — file does not exist yet" case and the "periodic update" case. The plan and implement phases handle in-flight updates via their own Phase 0.9 / Phase 9 sync checkpoints.
Follow this execution flow. Do NOT skip phases.
Phase 1 — Pre-flight State Detection
Classify specs/_defaults/registry.yaml into one of three states. This determines the rest of the flow.
Run:
{SCRIPT}
(uses scripts/bash/check-prerequisites.sh --paths-only --json to locate REPO_ROOT)
Then inspect $REPO_ROOT/specs/_defaults/registry.yaml:
| State | Definition | Next step |
|---|---|---|
| MISSING | File does not exist | Proceed to Phase 2. Warn the user: "I will discover defaults from your project manifests, confirm with you, and create the registry." |
| EMPTY | File exists, every leaf value is null / [] / ~ |
Proceed to Phase 2. Same user message. |
| POPULATED | At least one leaf has a real value | If user input was init, warn that the registry already has content and ask: [Re-discover + update] [Audit only] [Cancel]. If user input was update or audit, proceed accordingly. |
For the POPULATED path with "audit only", skip Phases 2–5 and go straight to Phase 6 (audit report), then stop without writing.
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 · 314 lines · 58 tokens per session scan A 240d3eb2ab01
registry is a command published in the GitHub repository Chappygo-OS/Atomic-Spec (10 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 4,180 once invoked, about $0.0003 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
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
cross-research
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage: /cross-research [--with | list | compare].
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].
ijfw-metrics
Show IJFW token / cost / session metrics over a time window. Reads .ijfw/metrics/sessions.jsonl via the ijfwmetrics MCP tool.