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 diagnosegit 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/diagnose)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/diagnose"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/diagnose/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/diagnose"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/diagnose.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 Prompt Injection · line 111 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00110 | $0.02176 |
| Opus 5.5 | $0.00044 | $0.00870 |
| Sonnet 5.5 | $0.00022 | $0.00435 |
| Haiku 4.5 | $0.00011 | $0.00218 |
Grade B, and why
diagnose scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Do NOT use /diagnose as an email-capture surface. If `~/.claude/.ai-brain-starter-email-on-file` is missing, that is fine and never a finding — the email is optional, and the only places it is ever asked are the setup in How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/diagnose
{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.
Tells you whether your second brain is healthy.
Why
Most "Claude is broken" reports trace to one of:
- CLAUDE.md missing or has no Vault Map
- Hooks not registered, so no auto context-loading
journal-index.jsonstale or malformed, so insights find nothing.ps1files lost their UTF-8 BOM, so Windows PowerShell crashes- ai-brain-starter is many commits behind, so the user is on stale logic
/diagnose checks all of these in ~5 seconds. It writes nothing, sends no network requests beyond a single git fetch, and exits with a status code so it can be wired into CI or cron.
What to do
-
Find the script:
{SKILL_DIR}/../../scripts/diagnose.sh(the starter repo root sits two levels above this skill's folder on every install shape). -
Run it. Pick the right one for the platform:
Mac / Linux:
bash "{SKILL_DIR}/../../scripts/diagnose.sh" # or pass an explicit vault: bash "{SKILL_DIR}/../../scripts/diagnose.sh" "/path/to/vault"Windows:
pwsh "{SKILL_DIR}/../../scripts/diagnose.ps1" # or: pwsh "{SKILL_DIR}/../../scripts/diagnose.ps1" -Vault "C:\path\to\vault"By default it uses
$VAULT_PATHif set, else the current directory. -
Read the output to the user in plain language. Don't dump the raw report unless they ask. Translate:
- All green: "Your vault is healthy. Nothing to do."
- Only WARNs: "Working, but $N things to clean up. Want me to fix them?" Then offer to fix the specific WARNs (re-build journal index, add Vault Map to CLAUDE.md, pull latest ai-brain-starter, etc).
- At least one FAIL: "Something is broken: [name the FAIL in one sentence]. I can fix it: [propose the fix]." Wait for confirmation, then fix.
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 · 118 lines · 110 tokens per session scan B e23752950a7a
diagnose is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (48 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 2,176 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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…
open
Boot the session, load context from the vault, and surface what matters.
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.
capsule-compact
Compact a long capsule chain. Walks parentcapsuleid backward from a head capsule; if chain >= 5, summarizes oldest 3 into a chain-summary capsule. Manual invocation.
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.
close
Commit the session to durable vault memory and prepare a clean resume point.