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/migrate-tasksWrote 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/migrate-tasks)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/migrate-tasks"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/migrate-tasks.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 | $0.00037 | $0.00907 |
| Opus 5 | $0.00018 | $0.00453 |
| Sonnet 5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
migrate-tasks 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/migrate-tasks — Task Migration Planner
새 seed 버전에 대해 기존 태스크 영향 분석
When to use
- After
/diff-specreveals AC/entity/action changes between seed versions - Before re-running
/decomposefor the new version (avoids losing context from prior tasks) - When an external requirement change forces breaking AC removal
Prerequisites
- Living Spec methodology active
.harness/ouroboros/tasks/exists with tasks from prior/decomposeruns- Both source and target seed versions must exist
Usage
/migrate-tasks --to 2 # auto-detect 'from' as latest version below 2
/migrate-tasks --from 1 --to 3 # explicit
/migrate-tasks # auto: from latest-1 to latest
Instructions
Delegate to the Python classifier; do not classify tasks by reading them yourself — the script's reference matching against seed signatures is more reliable than free-form LLM judgment.
Step 1 — Locate the script
.harness/methodologies/living-spec/scripts/migrate-tasks.py
Step 2 — Resolve --to if missing
If the user didn't specify --to, default to the highest-numbered seed:
ls .harness/ouroboros/seeds/seed-v*.yaml | sort -V | tail -1 | grep -oE 'v[0-9]+' | tr -d 'v'
Step 3 — Run
python3 .harness/methodologies/living-spec/scripts/migrate-tasks.py --to <version>
The script:
- Reads all
.harness/ouroboros/tasks/*.yaml(excludingmigration-plans/) - Compares each task's
references.{ac, entities, actions}against target seed's signatures - Classifies as: unchanged (refs intact), deprecated (refs removed), modified (placeholder for v0.2)
- Identifies added items: AC/entities/actions present in target seed but not covered by any task
- Saves to
.harness/ouroboros/tasks/migration-plans/migration-v{from}-to-v{to}.yaml
Step 4 — Report
Relay the script's stdout summary. Then surface follow-up recommendations:
| Category | Recommended next action |
|---|---|
unchanged |
No action needed — these tasks remain valid |
modified |
Review each — open the task and check whether AC tightening requires re-implementation |
deprecated |
Decide per-task: archive, delete, or replace. Suggest using /decompose --replace <task-id> once available |
added |
Run /decompose against the new seed version to generate covering tasks |
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.
- 6d ago First seen · 95 lines · 37 tokens per session scan A 9f9c45e24378
migrate-tasks is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 907 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
set-tracker
Set the issue tracker for the current project.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
fire-todos
Capture, list, and manage todos during work sessions.
fire-execute-plan
Execute a single plan with segment-based routing, per-task atomic commits, and test enforcement.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.
next
Suggest the most likely next workflow action based on current context.