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/methodologygit 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/methodology)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/methodology"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/methodology.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 | $0.00040 | $0.01215 |
| Opus 5 | $0.00020 | $0.00607 |
| Sonnet 5 | $0.00008 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
methodology 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/methodology — Methodology Plugin Manager
하네스(고정 게이트) 위에 사용자가 상황별로 골라 쓰는 개발 방법론 시스템
Concept
┌─────────────────────────────────────────┐
│ HARNESS CORE (always enforced) │
│ • 11 gates (security, layers, spec) │
│ • Hooks (post-edit, pre-commit) │
└─────────────────────────────────────────┘
▲
│ methodology can ADD gates,
│ cannot REMOVE core ones
│
┌─────────────────────────────────────────┐
│ METHODOLOGY LAYER (user-selected) │
│ ouroboros (default) | living-spec | │
│ parallel-change | bmad-lite | │
│ exploration | <custom> │
└─────────────────────────────────────────┘
Usage
/methodology # alias for `list`
/methodology list # show all installed methodologies + active state
/methodology current # show currently active methodology(ies)
/methodology info <name> # show one methodology in detail
/methodology use <name> # activate (replaces previous unless composing)
/methodology compose <a> <b> [...] # activate multiple methodologies together
/methodology deactivate <name> # turn off one methodology (other actives stay)
Instructions
You are the Methodology Dispatcher. Your job is to delegate to the shell library at .harness/lib/methodology.sh (or lib/methodology.sh if running from harness source) and report results clearly.
Step 1 — Locate the dispatcher script
Try in order:
.harness/lib/methodology.sh(installed in user project)lib/methodology.sh(running from harness source)
If neither exists, instruct the user to run init.sh (or re-run with --force) to install the methodology system, then stop.
Step 2 — Parse the user's subcommand
Map natural language to subcommands when needed:
- "show methodologies" / "what's available" / blank →
list - "what's active" / "current setup" →
current - "tell me about " / "details on " →
info <name> - "switch to " / "use " →
use <name> - "combine and " →
compose <a> <b> - "turn off " / "stop using " →
deactivate <name>
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 · 121 lines · 40 tokens per session scan A e83d37fc27b4
methodology is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,215 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.