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 longitudinalgit 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/longitudinal)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/longitudinal"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/longitudinal/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/longitudinal"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/longitudinal.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 | $0.00114 | $0.01332 |
| Opus 5.5 | $0.00046 | $0.00533 |
| Sonnet 5.5 | $0.00023 | $0.00266 |
| Haiku 4.5 | $0.00011 | $0.00133 |
Grade A, and why
longitudinal 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When the user types /longitudinal, run the multi-year correlation pass and surface only the strongest signals across years of health-mcp + journal data.
Language
Generate the report in the language the user writes in. If Spanish, all sections including the panel commentary are in Spanish.
Scope resolution
Parse the argument for window:
all-> earliest record in DB to todayNy-> last N years (e.g. 5y, 3y)Nm-> last N months (e.g. 18m)- blank -> 365 days
If all, query the DB for the earliest record date first:
SELECT MIN(start_date) FROM records WHERE value IS NOT NULL
Step 1: top_signals first (the noise filter)
Always call health_top_signals(vault_root=..., lookback_days=N, min_strength="moderate") first. This is Lara Briden's dissent codified: most correlations are noise. The substrate has already filtered. Start with what's left.
If signal_count == 0, report "no signals above noise threshold for this window" and stop — do not invent. Surface what IS there: the deltas and r-values that didn't quite clear the threshold, in case the user wants to relax it.
Step 2: Floor x body fingerprints for the user's top 3 Floors
Load the journal index, count Floors in the window, take the top 3 by occurrence.
For each Floor, call:
health_floor_body_fingerprint(floor=<name>, vault_root=..., lookback_days=N)
Report the body fingerprint deltas (HRV, RHR, sleep efficiency, cycle phase distribution). If delta_pct exceeds ±10% AND n_on_floor >= 10, this is a real fingerprint. Below that, mention it but flag as "weak."
Step 3: Sleep architecture trend
Call health_sleep_architecture(start, end) for the window AND for the prior matching window (e.g. 1y now vs 1y prior). Compare REM%, Deep%, Core%, efficiency. Flag drift > 5 percentage points.
Step 4: Longitudinal markers
Call health_longitudinal_summary(start, end, granularity="quarter"). Pull HRV baseline, VO2max, lean body mass, walking steadiness, sleep efficiency by quarter. Compute trend slope per marker (rough linear regression: (last - first) / first * 100).
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 · 102 lines · 114 tokens per session scan A 9a94c1e81713
longitudinal is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (48 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 1,332 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 2026-08-31.
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.