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/plangit 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 | $0.00014 | $0.13743 |
| Opus 5 | $0.00007 | $0.06871 |
| Sonnet 5 | $0.00003 | $0.02749 |
| Haiku 4.5 | $0.00001 | $0.01374 |
Grade A, and why
plan 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 — 1,554 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
- Setup: Run
{SCRIPT}from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH.
1.5. Pre-flight: detect unfinished earlier work (v0.3+, per Constitution Directive 9):
Check BOTH spec.md AND clarify-log.md (the latter only if it exists — clarify is optional). Either being in authoring_in_progress blocks planning.
scripts/bash/stamp-lifecycle.sh status "$FEATURE_SPEC" --json
# If clarify-log.md exists, also:
[ -f "$SPECS_DIR/$BRANCH/clarify-log.md" ] && scripts/bash/stamp-lifecycle.sh status "$SPECS_DIR/$BRANCH/clarify-log.md" --json
scripts\powershell\stamp-lifecycle.ps1 -Command status -Artifact "$FEATURE_SPEC" -Json
$clog = "$SPECS_DIR\$BRANCH\clarify-log.md"
if (Test-Path $clog) { scripts\powershell\stamp-lifecycle.ps1 -Command status -Artifact $clog -Json }
Parse each JSON. If ANY reports state=authoring_in_progress, ABORT with:
"Unfinished detected (artifact: , started by ). Run /atomicspec. to finish, or /atomicspec.implement for the full resume procedure."
This is the lightweight cross-phase guard. Only /atomicspec.implement performs the full Phase 0 Orientation.
- Load context: Read FEATURE_SPEC and
/memory/constitution.md. Load IMPL_PLAN template (already copied).
2.5. Stamp Lifecycle Markers — open authoring on plan.md (v0.3+):
IMPL_PLAN was just copied by setup-plan and contains the ## Lifecycle Markers heading. Initialize and open the authoring lifecycle:
scripts/bash/stamp-lifecycle.sh init "$IMPL_PLAN" --lifecycle authoring
scripts/bash/stamp-lifecycle.sh start "$IMPL_PLAN" --lifecycle authoring --provider {{AGENT_NAME}} --verify-depth deep
scripts\powershell\stamp-lifecycle.ps1 -Command init -Artifact "$IMPL_PLAN" -Lifecycle authoring
scripts\powershell\stamp-lifecycle.ps1 -Command start -Artifact "$IMPL_PLAN" -Lifecycle authoring -Provider {{AGENT_NAME}} -VerifyDepth deep
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 · 1,554 lines · 14 tokens per session scan A a6c0a0d13113
plan is a command published in the GitHub repository Chappygo-OS/Atomic-Spec (10 stars, last pushed 9d ago), licensed MIT. It adds 14 tokens to every session and 13,743 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
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.