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/Khar-AG/t-800-agentnpx agentmods add commands/khar-ag/t-800-agent/t800-plugin-auditWrote 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/khar-ag/t-800-agent/t800-plugin-audit)<a href="https://agentmods.dev/commands/khar-ag/t-800-agent/t800-plugin-audit"><img src="https://agentmods.dev/badge/commands/khar-ag/t-800-agent/t800-plugin-audit/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/khar-ag/t-800-agent/t800-plugin-audit"><img src="https://agentmods.dev/badge/commands/khar-ag/t-800-agent/t800-plugin-audit.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 | $0.00000 | $0.00906 |
| Opus 5 | $0.00000 | $0.00453 |
| Sonnet 5 | $0.00000 | $0.00181 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
t800-plugin-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/t800-plugin-audit — аудит одного Cursor-плагина
Зачем: карта agents / skills / commands / rules / hooks внутри --plugin-root (граф, orphans, alwaysApply) — без dump в KB T-800.
Loop / STATE: shared/loop-engineering-contract.md.
Шаги
0. Discovery + STATE
bash scripts/discover-target-project.sh --workspace "<WORKSPACE>" --plugin-root "<PLUGIN_ROOT>"
bash scripts/t800_loop_state.sh init --memory-path "<memory_path>"
# Read STATE.md — blockers / lessons прошлого аудита
Запомни memory_path целевого проекта. Runtime-отчёты → только {memory_path}/audits/.
1. Machine SoT (обязателен)
python3 scripts/t800_plugin_audit.py \
--plugin-root "<PLUGIN_ROOT>" \
--out "<memory_path>/audits/t800-plugin-audit-$(date +%Y%m%d-%H%M)" \
[--strict-alwaysapply large]
Пишет: inventory.json, scorecard.json, graph.md, audit-machine-summary.md.
Без inventory.json или при fail скрипта — не «готово» (machine gate).
bash scripts/t800_loop_state.sh touch --memory-path "<memory_path>" --stage "plugin-audit" --message "machine SoT: inventory.json"
2. Narrative
Task(t-800-plugin-auditor)
Передай: plugin_root, out (run-id dir), memory_path, уровень strict.
Агент читает JSON → audit-summary.md + fragments/t-800-plugin-auditor.md.
3. Fix-pack draft (после narrative)
python3 scripts/t800_audit_to_fixpack.py \
--audit-dir "<memory_path>/audits/<run-id>" \
--memory-path "<memory_path>" \
[--slug from-audit-$(date +%Y%m%d)]
Скрипт печатает путь {memory_path}/fix-packs/<slug>.md.
Дальше для правок: /t800-fix (не полный /t800-start, если список файлов уже в pack).
4. Закрытие STATE
bash scripts/t800_loop_state.sh touch --memory-path "<memory_path>" --stage "plugin-audit" --message "narrative готов; fix-pack draft; gates pass"
Обнови в STATE.md секции Completed / Lessons / Gates (plugin-audit inventory = pass|fail).
Отличия от /t800-audit
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 · 91 lines · 0 tokens per session scan A 37e84e15e471
t800-plugin-audit is a command published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 906 tokens. 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 2026-08-31.
Other commands, from other repositories
pn-audit-data
Design or review database schema — normalization, indexing strategy, migration plan, and data model decisions. Surgical command for database design. Use standalone or as part of pn-backend-audit.
pn-audit-performance
Identify and fix backend performance issues — N+1 queries, missing cache layers, blocking I/O, slow queries, and connection pool exhaustion. Surgical backend performance pass.
pn-delight
Add purposeful moments of joy, motion, and personality. Use when the design is correct and complete but feels flat and lifeless.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.
pn-audit-errors
Standardize error handling — consistent shapes, structured logging, correlation IDs, safe client responses. Surgical command for error handling. Use standalone or as part of pn-backend-audit.
pn-audit-security
OWASP-guided security review — auth posture, input validation, secrets, CORS, JWT, rate limiting. Surgical command for backend security. Use standalone or as part of pn-backend-audit.