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/implementgit 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 | $0.00021 | $0.12528 |
| Opus 5 | $0.00010 | $0.06264 |
| Sonnet 5 | $0.00004 | $0.02506 |
| Haiku 4.5 | $0.00002 | $0.01253 |
Grade A, and why
implement scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8000/api/docs | grep -q "openapi" && echo "API docs accessible" How it starts
The opening of the file, as written. The whole thing — 1,056 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).
⛔ CONTEXT PINNING RULES
STOP. Read this section before reading ANY files.
Per Constitution Article IX, Directive 3, during implementation you are:
| Action | Allowed | Forbidden |
|---|---|---|
| Read for navigation | index.md |
N/A |
| Read for current task | T-XXX-[name].md (ONE file only) |
Other task files |
| Update after completion | traceability.md |
N/A |
| Read project defaults | specs/_defaults/registry.yaml |
N/A |
| Read full specs | ❌ NEVER | plan.md, spec.md |
| Phase 0 Orientation (v0.3+) | Lifecycle Markers blocks (via stamp-lifecycle status ONLY) of every artifact in the feature folder — see Directive 9 |
Body content of plan.md, spec.md, clarify-log.md — even during orientation |
If you are about to read plan.md, spec.md, or clarify-log.md, STOP. You are violating Context Pinning.
Phase 0 Orientation is a one-shot carve-out (Directive 9): runs ONCE at session start, before any task loop. After Phase 0 completes (or finds the feature clean), normal Context Pinning resumes in full.
You MUST NOT invoke the Read tool on plan.md, spec.md, or clarify-log.md at any point during Phase 0. The ONLY permitted access to those artifacts in Phase 0 is via scripts/{bash,powershell}/stamp-lifecycle.{sh,ps1} status --json, which extracts the Lifecycle Markers block and returns JSON. Justifications such as "I need the heading first" or "just to find the block" are explicitly rejected — the status script already returns the structured block. Reading the body content of any of these three files during Phase 0 is a Constitution violation regardless of intent.
Outline
0. Orientation — Detect Partial Work (v0.3+, Directive 9)
This phase ONLY runs at session start. Its job: detect whether prior work on this feature was interrupted (Claude session crashed → Codex resumes; quota cut → Gemini picks up). If yes, present options and STOP for user confirmation. NEVER silently resume.
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 · 1,056 lines · 21 tokens per session scan A 3d4f650e67b9
implement is a command published in the GitHub repository Chappygo-OS/Atomic-Spec (10 stars, last pushed 9d ago), licensed MIT. It adds 21 tokens to every session and 12,528 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.