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 skills add Khar-AG/t-800-agent --skill t-800-run-gatesgit clone --depth 1 https://github.com/Khar-AG/t-800-agentWrote 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/skills/khar-ag/t-800-agent/t-800-run-gates)<a href="https://agentmods.dev/skills/khar-ag/t-800-agent/t-800-run-gates"><img src="https://agentmods.dev/badge/skills/khar-ag/t-800-agent/t-800-run-gates/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/skills/khar-ag/t-800-agent/t-800-run-gates"><img src="https://agentmods.dev/badge/skills/khar-ag/t-800-agent/t-800-run-gates.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 | $0.00089 | $0.00435 |
| Opus 5 | $0.00044 | $0.00217 |
| Sonnet 5 | $0.00018 | $0.00087 |
| Haiku 4.5 | $0.00009 | $0.00044 |
Grade A, and why
t-800-run-gates 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 9d 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.
What it actually says
T-800 — run gates (procedural matrix)
Канон: python3 scripts/t800_run_gate.py (+ флаги). Skill не заменяет скрипты.
Что читать
shared/loop-engineering-contract.md- T800-SYSTEM-MAP / docs gates table
scripts/t800_run_gate.py --help
Матрица: gate-matrix.md.
CREATE: strict-create.md.
Router modes: router-modes.md (shared/router-cost-policy-contract.md).
Алгоритм
- Classify mode: CREATE | PATCH | LOOP | AUDIT.
- Выбрать required checks из matrix.
- Запустить команды (не объявлять PASS заранее).
- Parse JSON / exit code.
- Обновить
STATE.md→ Gates. - PASS только при exit 0, когда check required.
Выход
mode: CREATE|PATCH|LOOP|AUDIT
commands_run: []
ok: true|false
blockers: []
STATE_updated: true|false
Запреты
- Self-PASS без machine evidence
- afterFileEdit / conversation hooks как sole production gate
- Silent skip
--strict-createна CREATE
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 57 lines · 89 tokens per session scan A c9c1980355cb
t-800-run-gates is a skill published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 16d ago), licensed MIT. It adds 89 tokens to every session and 435 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
pn-writing-skills
Applies TDD to skill authoring: validation scenarios first, then SKILL.md. Use when creating new skills, editing existing skills, or verifying skills work before deployment.
pn-best-of-n
Run 2–3 competing implementations of the same spec in isolated worktrees, eliminate failures via objective gates, then judge survivors with a separate premium-tier pass. Use for ambiguous algorithm/API/refactor choices with strong tests — not auth/security paths.
pn-slice-contracts
How to define and lock interface contracts between featureprogram slices, emit .cursor/worktrees.json, and run contract-conformance tests at the verifier gate. Use at featureprogram step 1 (lock contracts) and step 4 (verify conformance).
pn-systematic-debugging
Root cause analysis with triage mode — Phase 0 feedback loop, investigate first, one question max, then isolate, hypothesize, confirm. Outputs TDD fix plan with RED-GREEN cycles; optional GitHub issue via GitHub MCP. Use when debugging a failure or bug.
pn-loop
Autonomous iteration until verification passes. Keep working on the same task, re-running verification commands each turn, until they succeed. Use for fix-until-green, migration completion, or any task with clear verification criteria.
pn-testing-strategy
Testing strategy and pyramid. Unit/integration/E2E ratio, Vitest vs Playwright vs MSW, contract testing, and test-environment setup. Use when defining or reviewing a project's testing approach.