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 mycelium-hq/ai-brain-starter --skill security-snapshotgit clone --depth 1 https://github.com/mycelium-hq/ai-brain-starterWrote 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/mycelium-hq/ai-brain-starter/security-snapshot)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/security-snapshot"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/security-snapshot/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/mycelium-hq/ai-brain-starter/security-snapshot"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/security-snapshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00098 | $0.01590 |
| Opus 5.5 | $0.00039 | $0.00636 |
| Sonnet 5.5 | $0.00020 | $0.00318 |
| Haiku 4.5 | $0.00010 | $0.00159 |
Grade A, and why
security-snapshot 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{SKILL_DIR}= this skill's own folder (locally: the directory this SKILL.md lives in; a served brain substitutes the real absolute path before you read this). Shared starter files live at the repo root two levels up:{SKILL_DIR}/../... If a path does not resolve, name the missing file and stop — never guess another location.
When the user types /security-snapshot [domain] or asks for a security check on a prospect, run the security snapshot generator and deliver a client-ready report.
Why this skill exists
Prospects rarely have budget for a full security audit upfront, but they will read a free one-page report that exposes real issues with their public-facing setup. This skill generates that report in under 3 minutes and opens the door for a paid follow-up on security work, AI implementation, or adjacent consulting.
Command
python3 "{SKILL_DIR}/../../scripts/security-snapshot.py" <domain> --company "<Display Name>"
The script ships with the starter repo. Output goes to $SNAPSHOTS_DIR if set, otherwise $VAULT_ROOT/security-snapshots/ if VAULT_ROOT is set, otherwise a security-snapshots/ folder next to wherever you run the command from. It takes 60-180 seconds because SSL Labs is slow. The script prints the saved report path to stdout and progress to stderr.
Workflow
- Get the domain. If the user only gave a company name, ask for the domain (e.g., "Is it acme.com or acmecorp.com?"). Do not guess.
- Run the script. Use Bash with a long timeout (180000ms) because SSL Labs polling is slow.
- Read the output. The script saves to
$SNAPSHOTS_DIR/<domain>/<YYYY-MM-DD>-snapshot.md(defaults to$VAULT_ROOT/security-snapshots/whenSNAPSHOTS_DIRis unset). Read the file before summarizing. - Summarize for the user. Do NOT dump the full report into chat. Give:
- Top 3 findings by severity with one-line reasons
- SSL grade
- Whether SPF + DMARC are both present
- Path to the saved report
- Offer the follow-up. If there are high or critical findings, offer to draft the outreach email that pairs with the report. Match the user's own outreach voice, do not invent a new one.
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.
- 1mo ago First seen · 110 lines · 98 tokens per session scan A d3da6beea66e
security-snapshot is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (48 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 1,590 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
nightly
Canonical seven-leg nightly close-parity protocol. Eleven independently evidenced checkpoints cover synthesis, reconciliation, context hygiene, sweeps, heat, digest, runtime health, cognitive state, ledger capture/review, and vault sync.
Promote
Take a slice of the current conversation and promote it to a durable vault artifact — concept note, project update, person profile, or doctrine entry. Pairs with /close. /close writes the daily note (transient outcome record); /promote elevates specific insights to permanent vault content the framework can refer back…
Stuck
Walk the 6-rung escalation ladder before declaring stuck or asking the principal. Most "stuck" is actually "haven't tried the next approach." Stopping is the last resort, not the first response.
open
Boot the session, load context from the vault, and surface what matters.
caddy-mute
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
start
The day-one first-run flow and the everyday home screen. On first launch, greet, run setup, then carry the operator into a real first win. On return, give a short briefing and action menu.