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/studiokjm/ai-harness-template/parallel-changegit clone --depth 1 https://github.com/studioKjm/ai-harness-templateWrote 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/parallel-change)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/parallel-change"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/parallel-change.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 | $0.00045 | $0.00794 |
| Opus 5 | $0.00023 | $0.00397 |
| Sonnet 5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
parallel-change 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 5d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/parallel-change — Plan Manager
호환 깨는 변경을 다운타임 0으로 처리하는 상태머신
When to use
- DB 스키마 변경 (컬럼 타입·이름·제약 변경)
- API 시그니처 변경 (필수 파라미터 추가/제거)
- 함수/타입 시그니처 breaking change
/diff-spec이 🔴 Breaking-change indicator를 띄웠을 때
Prerequisites
- Parallel Change methodology active:
/methodology compose ouroboros parallel-change
Subcommands
/parallel-change new <id> [--title TITLE] Create new plan in phase=expand
/parallel-change list List all plans + current phase
/parallel-change show <id> Print full plan
For phase transitions, use the dedicated commands:
/expand— register/verify expand phase/migrate-traffic— advance to migrate/contract— advance to contract
Instructions
Delegate to the Python script. Do not hand-edit plan YAML files — they are state-machine artifacts owned by the dispatcher.
Step 1 — Locate the script
.harness/methodologies/parallel-change/scripts/pc.py
Step 2 — Resolve subcommand
python3 .harness/methodologies/parallel-change/scripts/pc.py new <id> --title "<title>"
python3 .harness/methodologies/parallel-change/scripts/pc.py list
python3 .harness/methodologies/parallel-change/scripts/pc.py show <id>
Step 3 — Plan ID convention
Use pc-<YYYY-MM-DD>-<short-slug> format. Example:
pc-2026-04-28-refund-amount-enum
pc-2026-04-28-orders-api-v2
Step 4 — After creating a plan
Guide the user through the next step:
-
Register the old signature (what's being replaced):
pc.py set-old <id> --symbol "Refund.amount" --pattern 'Refund\.amount\b' -
Implement the new signature alongside the old, then register:
pc.py set-new <id> --symbol "Refund.amount_type" --pattern 'Refund\.amount_type\b' -
When ready to transition:
/migrate-traffic(will validate expand criteria)
Step 5 — Caller pattern guidance
The caller_pattern is a regex passed to ripgrep/grep. Common examples:
| Target type | Pattern example |
|---|---|
| Property access | Refund\.amount\b |
| Function call | \boldFunction\s*\( |
| API endpoint | POST\s+/api/v1/refunds |
| DB column | \brefunds\.amount\b |
| Type/Class name | \bOldType\b |
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.
- 5d ago First seen · 104 lines · 45 tokens per session scan A 0df2cbef5e4c
parallel-change is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 794 once invoked, about $0.0002 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
VibeGuard: ExecPlan
Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
VibeGuard: Live Truth
Verify live claims with fresh facts, inferences, and unresolved gaps.
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
harness-adopt
Apply Harness Starter Kit to the current target repository with the prompt-first adoption workflow.