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/TserenTserenov/FMT-exocortex-templatenpx agentmods add skills/tserentserenov/fmt-exocortex-template/audit-installationWrote 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/tserentserenov/fmt-exocortex-template/audit-installation)<a href="https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/audit-installation"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/audit-installation/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/tserentserenov/fmt-exocortex-template/audit-installation"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/audit-installation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00135 | $0.03895 |
| Opus 5.5 | $0.00054 | $0.01558 |
| Sonnet 5.5 | $0.00027 | $0.00779 |
| Haiku 4.5 | $0.00014 | $0.00390 |
Grade A, and why
audit-installation 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 2d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Аудит инсталляции IWE
Service Clause: VR.SC.005-installation-audit Роль: VR.R.002 Аудитор (PACK-verification) — субагент с context isolation Принцип: детектор отчитывается, оператор делает (см.
scripts/iwe-drift.sh:7-11). Auto-fix не входит в обещание.
Аргументы: $ARGUMENTS
When to use
Аудит пользовательской инсталляции IWE. Запускает scripts/iwe-audit.sh + MCP healthcheck + smoke-test ритуала через sentinel-механику (контракт dry-run-contract.md), передаёт отчёт subagent'у в роли VR.R.002 Аудитор (context isolation) → verdict ✅/⚠️/❌ по 6 компонентам (Inventory, L1 drift, {{GOVERNANCE_REPO}}, L3 customizations, MCP, ритуал). Используй после restore из бэкапа, после update.sh, или при еженедельной сверке.
Обещание
За ≤5 минут — markdown-отчёт ✅/⚠️/❌ по 6 компонентам инсталляции:
- Inventory — все ли критичные L1-файлы (CLAUDE.md, скиллы, протоколы) на месте
- L1 drift — расхождения с FMT-exocortex-template
- {{GOVERNANCE_REPO}} — git status + diff с FMT-strategy-template
- L3 customizations — extensions/, отличия params.yaml от skeleton, AUTHOR-ONLY зоны
- MCP healthcheck — 4 tools отвечают (с уважением к подписочному гейтингу DP.SC.112)
- Ритуал smoke-test —
/run-protocol close dayзапускается под sentinel-защитой, доходит до write-шагов (см.memory/dry-run-contract.md)
Verdict выносит subagent в роли Аудитора, читая отчёт без знаний о текущей сессии (context isolation).
Шаг 1. Детерминированные проверки (bash)
Найти и запустить iwe-audit.sh через fallback-цепочку (author-mode → workspace, user-mode → $IWE_SCRIPTS из ~/.iwe-paths):
# issue #688: a non-interactive top-level Bash call doesn't go through
# .bashrc/.zshenv (interactive-shell guard) or BASH_ENV (read before the
# harness can set it) — $IWE_SCRIPTS is unset here on plenty of real
# installs even though ~/.iwe-paths exists and is correct. Source it
# directly, in this same shell, before reading the variable — `.` doesn't
# depend on interactive/BASH_ENV machinery at all.
# issue #932: the installer writes <workspace>/.iwe-paths (install-iwe-paths.sh);
# $HOME/.iwe-paths is the legacy location, tried last.
IWE_PATHS="${IWE_PATHS_FILE:-}"
if [ -z "$IWE_PATHS" ]; then
for _c in "${IWE_WORKSPACE:-}/.iwe-paths" "${WORKSPACE_DIR:-}/.iwe-paths" \
"$PWD/.iwe-paths" "${IWE_WORKSPACE:-$HOME/IWE}/.iwe-paths" "$HOME/.iwe-paths"; do
[ -r "$_c" ] && { IWE_PATHS="$_c"; break; }
done
fi
[ -n "$IWE_PATHS" ] && [ -r "$IWE_PATHS" ] && . "$IWE_PATHS"
if [ -n "${IWE_SCRIPTS:-}" ] && [ -f "$IWE_SCRIPTS/iwe-audit.sh" ]; then
# $IWE_SCRIPTS first (#566): the hardcoded workspace copy, when it exists at
# all, is a stale leftover — the installer points IWE_SCRIPTS at the template.
AUDIT_SCRIPT="$IWE_SCRIPTS/iwe-audit.sh"
elif [ -f "${IWE_WORKSPACE:-$HOME/IWE}/scripts/iwe-audit.sh" ]; then
AUDIT_SCRIPT="${IWE_WORKSPACE:-$HOME/IWE}/scripts/iwe-audit.sh"
else
echo "iwe-audit.sh не найден. \$IWE_PATHS ($IWE_PATHS) не даёт рабочий \$IWE_SCRIPTS — проверь, что файл существует и содержит export IWE_SCRIPTS=... (запусти setup.sh из FMT-шаблона, если файла нет)."
exit 1
fi
bash "$AUDIT_SCRIPT" $([ "${ARGUMENTS:-}" = "--critical" ] && echo "--critical")
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.
- 2d ago Changed · +4 tokens per session 9fa20f64a36b
- 3d ago Changed 3942749b9c6e
- 12d ago Changed · +10 lines 5751a3818773
- 1mo ago Changed · +8 lines 0d1e7dfb68f7
- 1mo ago Changed · +1 lines 650596be9560
- 1mo ago Changed · -13 lines 2ab7fc246cdd
- 1mo ago First seen · 255 lines · 131 tokens per session scan A 931d80593488
audit-installation is a skill published in the GitHub repository TserenTserenov/FMT-exocortex-template (63 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 3,895 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
paired-probe
Refuse a verdict a probe did not earn. Runs a check where the fault IS present and where it is NOT, and blocks the answer when both arms print the same thing, because a check that cannot disagree with you has measured nothing. Also catches the zero-sample sweep that reads as "clean" and the swallowed error that reads…
testing
Writing effective tests and running them successfully. Covers layer-specific mocking rules, test design principles, debugging failures, and flaky test management. Use when writing tests, reviewing test quality, or debugging test failures.
pdlc-fix
An automated bug-fixing workflow that locates a reported bug, reproduces it with a test, applies a minimal fix, runs tests, and updates the relevant documentation.
team-management-debugging
Systematic debugging — a four-phase root-cause methodology, boundary instrumentation for multi-component systems, the 3-fix escalation rule, and a verification gate to run before claiming anything is fixed. Use on any test failure, production bug, build failure, performance regression, or integration glitch, and…