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 skills/davidmatousek/tachi/aod-stacknpx skills add davidmatousek/tachi --skill aod-stackgit clone --depth 1 https://github.com/davidmatousek/tachiWhat 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 | $0.00042 | $0.04526 |
| Opus 5 | $0.00021 | $0.02263 |
| Sonnet 5 | $0.00008 | $0.00905 |
| Haiku 4.5 | $0.00004 | $0.00453 |
Grade A, and why
aod-stack 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aod-stack — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stack Pack Management Skill
Activate, list, and manage stack packs that encode technology-specific conventions, security patterns, and agent persona supplements into AOD.
Subcommands
| Command | Purpose |
|---|---|
/aod.stack use {pack-name} |
Activate a stack pack |
/aod.stack list |
Show available packs and active status |
/aod.stack remove |
Deactivate the active pack |
/aod.stack scaffold |
Scaffold project structure from the active pack |
/aod.stack use {pack-name}
Activate a stack pack by copying its rules, generating a persona loader, and persisting activation state.
Step 1: Validate the pack exists
- Check that
stacks/{pack-name}/exists as a directory. - Check that
stacks/{pack-name}/STACK.mdexists and is non-empty. - If the directory or STACK.md does not exist, display the error:
Then stop.Pack not found: {pack-name} Available packs: - {list each directory under stacks/ that contains a STACK.md} Use: /aod.stack use {pack-name}
Step 2: Handle already-active pack
- Read
.aod/stack-active.jsonif it exists. - If another pack is active (the
packfield differs from{pack-name}):- Prompt the user: "Pack
{current-pack}is currently active. Switch to{pack-name}? This will deactivate{current-pack}first. (y/n)" - If the user declines, stop.
- If the user confirms, execute full deactivation:
a. Delete all files in
.claude/rules/stack/. b. Delete.aod/stack-active.json.
- Prompt the user: "Pack
- If the same pack is already active (
packfield equals{pack-name}):- Prompt: "Pack
{pack-name}is already active. Re-activate to update rules and persona loader? (y/n)" - If the user declines, stop.
- If the user confirms, proceed (this refreshes rules from the pack source).
- Prompt: "Pack
Step 3: Detect and resolve inconsistent state
Before proceeding, check for inconsistencies:
- If
.aod/stack-active.jsonexists but is not valid JSON:- Warn: "Inconsistent state:
.aod/stack-active.jsonis corrupted. Cleaning up stale state." - Delete all files in
.claude/rules/stack/. - Delete
.aod/stack-active.json. - Then continue with activation.
- Warn: "Inconsistent state:
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 First seen · 501 lines · 42 tokens per session scan A bc455dab8d27
aod-stack is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 20d ago), licensed Apache-2.0. It adds 42 tokens to every session and 4,526 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 skills, from other repositories
testing-mcp-server-security
Testing Model Context Protocol (MCP) servers and the clients that consume them for tool poisoning, prompt injection via tool descriptions/outputs, over-permissioned and local-credential-stealing tools, config/trust bypasses, and unauthenticated RCE during authorized penetration tests of AI agent infrastructure.
container-image-scan
USAP agent skill for Container Image Scan. Use for classifying container-image vulnerability scan findings from Trivy, Grype, or Snyk into a block-deploy, fix-by-SLA-window, track, or accept decision across base-image OS packages, application dependencies, and unexpected image layers.
security-requirements-review
USAP agent skill for Security Requirements Review. Use for proactive analysis of design documents — POA&M, PRDs, architecture docs, requirements specs — to extract security gaps before any alerts fire.
cloud-security-posture
USAP agent skill for Cloud Security Posture. Use for Evaluate cloud misconfigurations and posture drift.
attack-surface-management
USAP agent skill for Attack Surface Management. Use for Continuously discover and assess exposed assets.
behavioral-analytics
USAP agent skill for Behavioral Analytics (UEBA). Use for Analyze behavioral anomalies across users and entities.