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 sunday-reviewgit 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/sunday-review)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/sunday-review"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/sunday-review/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/sunday-review"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/sunday-review.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 | $0.00102 | $0.04377 |
| Opus 5.5 | $0.00041 | $0.01751 |
| Sonnet 5.5 | $0.00020 | $0.00875 |
| Haiku 4.5 | $0.00010 | $0.00438 |
Grade A, and why
sunday-review 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sunday-review — weekly meta-orchestrator
{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.
You are running the Sunday meta-review. This skill doesn't reinvent the existing weekly skills — it orchestrates them in the right sequence, surfaces the cross-cutting signal, and produces ONE clean note instead of N independent reports.
Order of operations
Run each step in order. After each step, capture the headline finding (1-2 sentences) into the running synthesis. Do NOT dump full reports inline — link to them.
Step 1 — Pattern recognition (/weekly)
Invoke the existing /weekly insights skill. It produces the panel-driven journal pattern recognition for the past 7 days. Capture: which floor was dominant, what pattern repeated, what was avoided.
Step 2 — Instinct Engine (/patterns)
Invoke /patterns. It scans recent sessions, journals, and decisions for hardening patterns and turns them into concrete captures. Capture: any new patterns ready to codify into a CLAUDE.md rule, concept note, or skill improvement.
Step 3 — Vault hygiene scan
Run:
python3 "{SKILL_DIR}/../../scripts/vault-hygiene.py" --quiet
It writes a fresh report to ⚙️ Meta/Vault Hygiene.md. Capture: how many broken wikilinks, empty notes, stale notes, duplicate concepts.
Step 3b — Backup restore drill (NO SKIP)
Run:
bash "{SKILL_DIR}/../../scripts/vault-backup.sh" verify --vault "$VAULT_ROOT"
verify decrypts the newest snapshot into a temp dir, extracts it, and counts the files. It is the only backup check that opens the archive. Three outcomes, three different reports:
- Exit 0 — capture the file count restored and the snapshot's date. A count far below the vault's real file count is a FAIL, not a pass.
- Exit non-zero saying
vault not configuredorno snapshot found— there is no backup at all. That is the week's one thing to do; give the setup command:bash "{SKILL_DIR}/../../scripts/vault-backup.sh" setup --vault "$VAULT_ROOT". - Any other non-zero — an archive exists and does not restore. FAIL.
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 · 259 lines · 102 tokens per session scan A 71e7ba504a06
sunday-review is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (48 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 4,377 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 2026-09-04.
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.