Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add studioKjm/ai-harness-template/plugin install harnessWrote 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)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/strangler"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/strangler.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 | $0.00022 | $0.01250 |
| Opus 5 | $0.00011 | $0.00625 |
| Sonnet 5 | $0.00004 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
strangler 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/strangler — Module-level Legacy Migration
Replace a legacy module gradually via a facade — coexist, then cut over, then retire.
When to use
- Legacy module is too risky for full rewrite
- Multiple consumers/endpoints — can't migrate atomically
- New implementation will replace legacy over weeks/months
- Want graceful rollback at each phase
Not for:
- Single-function signature change → use
parallel-change(it's function-level) - Greenfield work → use
ouroboros(no legacy to strangle) - One-shot rewrite where downtime is acceptable → just rewrite
Usage
/strangler new <slug> --legacy <path> --new <path> --facade <path> [--title "..."]
/strangler list [--state legacy-only|coexist|new-primary|retired]
/strangler show <plan-id>
/strangler advance <plan-id> <state> [--note "..."] [--force]
For routing rules:
/strangler-route add <plan-id> --pattern "..." --target legacy|new [--reason "..."]
/strangler-route remove <plan-id> --rule-id <id>
For final retirement:
/strangler-retire <plan-id>
Prerequisites
None. Strangler-fig is usable any time.
Instructions
Step 1 — Locate the script
.harness/methodologies/strangler-fig/scripts/sf.py
Step 2 — Run the requested subcommand
python3 .harness/methodologies/strangler-fig/scripts/sf.py \
new billing-rewrite \
--legacy "src/legacy/billing/" \
--new "src/billing/" \
--facade "src/billing-facade/" \
--title "Replace 2018 billing module with v2 architecture"
Step 3 — Communicate state changes
After new:
"Strangler plan
{id}created. State: legacy-only. Build the facade and at least one routed pattern in the new module before advancing. Add routing rules with/strangler-route add {id} --pattern '...' --target new."
After advance:
"Plan
{id}: {from} → {to}. {N} routing rules. Coverage {pct}%. {next-step hint based on state}"
State-specific guidance:
- legacy-only → coexist: "Now run traffic in production. Monitor for 1-2 weeks before advancing."
- coexist → new-primary: "Verify no incidents from new module in last 14 days. Performance parity check passed?"
- new-primary → retired: "Confirm legacy module has 0 inbound traffic for 30+ days before deletion."
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 · 137 lines · 22 tokens per session scan A 097b2e1a13ca
strangler is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 1,250 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
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.