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/threatWrote 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/threat)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/threat"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/threat.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 | $0.01516 |
| Opus 5 | $0.00011 | $0.00758 |
| Sonnet 5 | $0.00004 | $0.00303 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
threat 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 8d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/threat — STRIDE Threat Modeling
Assume the attacker has read your spec. Threat-model BEFORE you code, not after.
When to use
- Story/feature touches sensitive entity (auth, payment, PII, admin)
- New endpoint added (especially webhooks, public APIs)
- Architecture change affects trust boundaries
- Compliance requirement (PCI-DSS, GDPR, internal security policy)
Usage
/threat new <slug> --target-kind story|spike|feature|endpoint|module --target-ref REF
/threat list [--status draft|reviewed|approved|applied]
/threat show <model-id>
/threat add <model-id> --category S|T|R|I|D|E --threat "..." --mitigation "..." [...]
/threat review <model-id> # draft → reviewed (validates STRIDE coverage)
/threat approve <model-id> # reviewed → approved
/threat apply <model-id> # approved → applied
/threat link <model-id> --to story-id|spike-id|adr-id
/threat scan [--path GLOB] # find sensitive paths without threat model
STRIDE — what each letter means
| Letter | Category | Example threats |
|---|---|---|
| S | Spoofing | Impersonation, credential stuffing, session hijack |
| T | Tampering | Data modification in transit/storage, parameter tampering |
| R | Repudiation | User denies action, missing audit log, untrusted timestamps |
| I | Information Disclosure | Data leak, verbose errors, side-channel, IDOR |
| D | Denial of Service | Flood, resource exhaustion, algorithmic complexity |
| E | Elevation of Privilege | Privilege escalation, IDOR with admin actions, path traversal |
State machine
[draft] → [reviewed] → [approved] → [applied]
↓ ↓
[draft] [reviewed] (rollback allowed)
| State | Meaning | Move when |
|---|---|---|
| draft | Analysis in progress | All STRIDE categories addressed |
| reviewed | STRIDE coverage validated | Stakeholder approval |
| approved | Ready to implement | Mitigations shipped |
| applied | Mitigations live | (terminal) |
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.
- 8d ago First seen · 152 lines · 22 tokens per session scan A 3c771685dac8
threat 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 1,516 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.