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 humanerd-drew/opencode-drewgent --skill filesystem-truth-auditgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/filesystem-truth-audit)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/filesystem-truth-audit"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/filesystem-truth-audit.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 | $0.00000 | $0.01481 |
| Opus 5 | $0.00000 | $0.00740 |
| Sonnet 5 | $0.00000 | $0.00296 |
| Haiku 4.5 | $0.00000 | $0.00148 |
Grade A, and why
filesystem-truth-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 3d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: filesystem-truth-audit description: memory/vault의 "Done" path claim이 실제 filesystem에 존재하는지 검증 title: Filesystem Truth Audit — Memory vs Reality 검증 type: skill space: growth tags: [skill, filesystem-truth, audit, memory, vault, diagnostics] created: 2026-06-01 updated: 2026-06-01 links:
- "[[@identity/brain/{{AGENT_NAME}}-brain/P0-brainstem/禁/禁filesystem_truth.neuron]]"
- "[[@identity/SELF_MODEL]]"
- "[[@action/gateway/{{AGENT_NAME_LOWER}}-architecture-dataflow]]"
- "[[@identity/brain/rules]]"---
Filesystem Truth Audit — Memory vs Reality 검증
memory/vault/위키에 적힌 "Done" 또는 "exists" 항목이 실제 filesystem에 존재하는지 검증하는 스킬. P0-brainstem filesystem_truth 강제.
Trigger
다음 중 하나:
- memory에 있다고 했는데 실제로 없음 의심
- root consolidation / source dir 이동 / rename 이후 검증
- 새 skill/tool/script의 path를 memory에서 인용할 때
- filesystem = truth 점검 요청
Procedure
Step 1: Claim 추출
memory/vault에서 path claim 찾기:
grep -rn "Done" ~/.{{AGENT_NAME_LOWER}}/P0-brainstem ~/.{{AGENT_NAME_LOWER}}/P4-cortex ~/.{{AGENT_NAME_LOWER}}/P2-hippocampus 2>/dev/null | head -20
grep -rn "tools/.*\.py" ~/.{{AGENT_NAME_LOWER}}/P4-cortex/growth 2>/dev/null | head -10
"tools/{{AGENT_NAME_LOWER}}_kanban_db.py (Phase 1) Done" 같은 줄 추출.
Step 1b: Config value claim 추출
memory/vault에서 config value claim (config 변경 사실) 찾기:
# threshold 같은 config 변경 claim
grep -rn "threshold:" ~/.{{AGENT_NAME_LOWER}}/P4-cortex/growth 2>/dev/null | head -10
grep -rn "0.5 → 0.9\|0.5 -> 0.9" ~/.{{AGENT_NAME_LOWER}}/P4-cortex ~/.{{AGENT_NAME_LOWER}}/P6-prefrontal 2>/dev/null | head -10
grep -rn "applied\|patched\|configured" ~/.{{AGENT_NAME_LOWER}}/P4-cortex/growth 2>/dev/null | head -10
"compression.threshold: 0.5 → 0.9 (2026-05-21)" 같은 줄 추출.
Step 2: Real filesystem 검증
# 2a. 단일 path 직접 확인
test -f ~/.{{AGENT_NAME_LOWER}}/source/{{AGENT_NAME_LOWER}}-agent/tools/{{AGENT_NAME_LOWER}}_kanban_db.py && echo EXISTS || echo MISSING
# 2b. 이름으로 전체 검색
find ~/.{{AGENT_NAME_LOWER}} -name "{{AGENT_NAME_LOWER}}_kanban_db.py" -type f 2>/dev/null
# 2c. wildcard 패턴 검증
ls ~/.{{AGENT_NAME_LOWER}}/source/*/tools/*.py 2>/dev/null | wc -l
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.
- 3d ago First seen · 124 lines · 0 tokens per session scan A f28e1556c9db
filesystem-truth-audit is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,481 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 2026-09-03.
Other skills, from other repositories
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
exploiting-linux-kernel-vulnerabilities
Methodology for discovering and exploiting Linux kernel memory-corruption vulnerabilities (UAF, OOB read/write, race/TOCTOU, type confusion) during authorized engagements, covering reachability analysis, building stable read/write primitives from a single bug, defeating KASLR/SMEP/SMAP/KPTI, slab/buddy heap grooming…