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 deconstructgit 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/deconstruct)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/deconstruct"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/deconstruct/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/deconstruct"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/deconstruct.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 | $0.00101 | $0.02076 |
| Opus 5.5 | $0.00040 | $0.00830 |
| Sonnet 5.5 | $0.00020 | $0.00415 |
| Haiku 4.5 | $0.00010 | $0.00208 |
Grade A, and why
deconstruct 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deconstruct -- First Principles Analysis
A structured thinking skill modeled on Aristotle's method: find the foundational truths that cannot be derived from anything more basic, then reason upward from those truths alone.
When This Fires
- Manual: User types
/deconstructand describes a problem, decision, or situation - Auto-triggered (fast mode, optional): When logging a decision with
stakes: highin any decision template, Claude can auto-offer: "This is high-stakes. Want me to deconstruct it before you commit?" If yes, run fast mode (Phase 1 + Phase 4 only). To enable, adddeconstruct_auto: trueto your decision template frontmatter. - Auto-triggered (panel integration, optional): If your vault has an advisory panel skill (like the daily-journal plugin), add a trigger row for convention-following language. When the user says "that's how it's done," "best practice," "everyone does it this way," or copies a competitor's approach without questioning why, one panel voice surfaces 1-2 hidden assumptions in one sentence, then asks: "Is that actually true for YOU, or is it convention?"
Two Modes
Fast Mode (default for auto-triggers)
Phase 1 (surface assumptions) + Phase 4 (high-leverage move). Use for daily decisions and anything where the full run would be overkill.
Full Mode (default for /deconstruct)
All four phases in sequence. Use for pricing models, business models, career decisions, hiring processes, strategy pivots, and anything where "that's how it's done" is load-bearing in the current approach.
How It Works
When invoked manually via /deconstruct, start by asking:
"Describe the problem, decision, or situation you want me to deconstruct. Include enough context that I can distinguish your actual constraints from your assumptions. Tell me what you know is true and what you believe is true."
If the problem is too vague to deconstruct meaningfully, ask 1-2 clarifying questions. Do not guess.
Then execute the phases in order. Complete each phase fully before moving to the next.
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 · 184 lines · 101 tokens per session scan A ccc1dab06aea
deconstruct is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (47 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 2,076 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.
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.
caddy-mute
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.