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/strangler-retireWrote 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/strangler-retire)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/strangler-retire"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/strangler-retire/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/strangler-retire"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/strangler-retire.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.00932 |
| Opus 5 | $0.00012 | $0.00466 |
| Sonnet 5 | $0.00005 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
strangler-retire 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/strangler-retire — Final Retirement Check
The point of no return. After retire, legacy module is deleted.
When to use
- All routing rules target
new - Coverage = 100%
- Legacy module has had 0 inbound traffic for 30+ days (manually verified)
- Ready to delete legacy code from the repository
This is the highest-stakes transition. Misuse means deleting code that's still serving production traffic.
Prerequisites
- Plan in
new-primarystate - All
routing_ruleshavetarget: new coverage.percent== 100- (Manual) production telemetry confirms legacy module has 0 calls
Usage
/strangler-retire <plan-id>
This is an alias for /strangler advance <plan-id> retired.
Instructions
Step 1 — Pre-flight check
Before advancing:
python3 .harness/methodologies/strangler-fig/scripts/sf.py show <plan-id>
Verify:
- All routing rules
target: new coverage.percent: 100coverage.unrouted: []
Step 2 — Manual verification (off-system)
The methodology cannot check production traffic. The user MUST verify before retiring:
- Application logs / APM: 0 calls to legacy module functions in last 30 days
- Database query logs (if applicable): 0 reads from legacy-specific tables
- Feature flag system (if used): legacy paths fully disabled
- Stakeholder sign-off (for client projects): client has reviewed cutover
Step 3 — Run retire
python3 .harness/methodologies/strangler-fig/scripts/sf.py retire <plan-id>
The script enforces (auto):
- Plan in
new-primarystate - All rules target
new - Coverage 100%
If any check fails, the script blocks. Use --force only with explicit reason recorded.
Step 4 — Post-retire actions
After advancing to retired:
"Plan
{id}retired. You may now safely delete the legacy module:
- Remove
{legacy_module.path}directory in a separate commit- Update facade to remove legacy fallback code
- If facade itself becomes unnecessary, remove it after one more cycle
- Mark related ADRs as superseded"
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.
- 10d ago First seen · 110 lines · 24 tokens per session scan A 4d0753440475
strangler-retire is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 932 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.
show-lessons
Display promoted lessons and their corrective actions.
harness-review
Review the current change set from an opposing harness-engineering perspective.
step0-specify-feature
Pipeline Step 0 — Specify what you want to build and why, before any technical planning. Surfaces ambiguities early with [NEEDS CLARIFICATION] markers.
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.