Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/studioKjm/ai-harness-templatenpx agentmods add commands/studiokjm/ai-harness-template/expandWrote 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/studiokjm/ai-harness-template/expand)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/expand"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/expand.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 5.1 | $0.00029 | $0.00559 |
| Opus 5 | $0.00015 | $0.00280 |
| Sonnet 5 | $0.00006 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
expand 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 7d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/expand — Verify Expand Phase
Expand 단계: 신·구 시그니처 공존 상태 확인
When to use
- Right after creating a plan with
/parallel-change new <id>and registering both old/new signatures - Before running
/migrate-traffic(this verifies the expand-phase invariants are met)
Prerequisites
- Plan exists in
phase=expand old.caller_patternandnew.caller_patternset in the plan
Usage
/expand <plan-id>
Instructions
This command does NOT advance phase — it only verifies expand criteria and reports caller counts.
Step 1 — Locate the script
.harness/methodologies/parallel-change/scripts/pc.py
Step 2 — Run callers count
python3 .harness/methodologies/parallel-change/scripts/pc.py callers <plan-id>
This prints:
- Caller count of OLD pattern (should be > 0 in expand phase)
- Caller count of NEW pattern (should be > 0 if implementation started)
Step 3 — Report
Surface the count to the user. Add interpretation:
| OLD callers | NEW callers | Interpretation |
|---|---|---|
| > 0 | > 0 | ✅ Expand healthy — both coexist |
| > 0 | 0 | ⏳ New not yet implemented — finish implementation before /migrate-traffic |
| 0 | > 0 | ⚠ Old already gone — was migration done out-of-band? Use pc.py advance <id> contract |
| 0 | 0 | ❌ Patterns wrong or change abandoned — re-check caller_pattern |
Step 4 — Suggest next step
If healthy expand:
"Expand verified. When all callers are ready to switch, run
/migrate-traffic <plan-id>"
If new not yet present:
"Implement the new signature alongside the old, then re-run /expand"
Constraints
- /expand never modifies the plan beyond updating
last_checktimestamps - /expand does not advance phase — that's
/migrate-traffic's job - Pattern false positives can inflate counts — adjust regex specificity if numbers seem off
Notes
- The
check-parallel-state.shgate runs this same logic on every commit and BLOCKS commits that put a plan in inconsistent state. So you don't need to run /expand manually before each commit — it just helps you understand current state on demand.
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.
- 7d ago First seen · 73 lines · 29 tokens per session scan A 0f2ee9053d69
expand is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 559 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 2026-08-30.
Other commands, from other repositories
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
show-lessons
Display promoted lessons and their corrective actions.
harness-review
Review the current change set from an opposing harness-engineering perspective.
harness-update
Update a target repository's harness from the latest harness-starter-kit reference material.
harness-doctor
Run Harness Doctor to evaluate how ready the current repository is for reliable AI coding agent collaboration.