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 pastarita/coer-nucleus --skill coer-recongit clone --depth 1 https://github.com/pastarita/coer-nucleusWrote 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/pastarita/coer-nucleus/coer-recon)<a href="https://agentmods.dev/skills/pastarita/coer-nucleus/coer-recon"><img src="https://agentmods.dev/badge/skills/pastarita/coer-nucleus/coer-recon/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/pastarita/coer-nucleus/coer-recon"><img src="https://agentmods.dev/badge/skills/pastarita/coer-nucleus/coer-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00095 | $0.00774 |
| Opus 5 | $0.00048 | $0.00387 |
| Sonnet 5 | $0.00019 | $0.00155 |
| Haiku 4.5 | $0.00010 | $0.00077 |
Grade A, and why
coer-recon 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 12d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoER Reconnaissance
Take a fuzzy domain interest and produce a structured landscape — the company tiers, the centers of excellence, the established players, and (most importantly) the emerging fringe talent — conforming to the CoER dashboard schema, then save it into the atlas.
What you produce
A single JSON object validating against schema/dashboard.schema.json, written to
corpus/domains/<slug>.json. Every panel of the CoER template maps to a field; see
procedure/METHOD.md for the field-by-field contract.
Procedure (the cascade)
Run procedure/madlib-prompts.md in order. It is a fuzzy cascade, not a strict pipeline —
revisit earlier panels when a later step teaches you something new.
- Intake — resolve the raw interest into
domain(name, industryContext, focusAreas, geographicFocus, timeHorizon, researchObjectives). Ask at most 2 clarifying questions, and only ifdomainorresearchObjectivesare genuinely underspecified. - Step 1 — Paradigm Shifts:
from → to, plus the talent signal each implies. - Step 2 — Competencies & Skills: knowledge domains + concrete practitioner skills.
- Step 3 — Industry & Centers: companies (established / prime movers / disruptors), geo-located centers of excellence, and industry organizations. Cover academia, industry, and individual enthusiast/creator/community projects.
- Step 4 — Key Players: established contributors with a truncated background timeline.
- Step 5 — Other Players: the long tail (citations, OSS, YouTubers, podcast guests).
- Step 6 (most important) — Potential Hires: emerging fringe talent, ranked by Creative Enthusiasm · Grit · Precociousness.
Run the while-loops throughout — they are your standing sourcing directives, not a
separate phase. While executing every step, perspicaciously source logos, links, names, and
entities, and resolve each into an indexable → rankable → presentable record: a stable key,
the evidence that lets it be ranked (source count, recency, traction, the Step-6 signals), and
the hyperlinks/fields its panel renders. The loops are: collect links, collect logos, dedupe
the typed common-skills list, and compile the Meta-Role-Description (roleResponsibilities).
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.
- 12d ago First seen · 53 lines · 95 tokens per session scan A 67afd35d7b81
coer-recon is a skill published in the GitHub repository pastarita/coer-nucleus (1 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 774 once invoked, about $0.0005 per session on Opus 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
add-provider
Add a new storage or service provider to the core package. Use when implementing a new backend for StorageService (e.g., a new database) or a new service provider (e.g., a new LLM backend).
add-export
Add a new subpath export to the @cyanheads/mcp-ts-core package. Use when creating a new public API surface that consumers import from a dedicated subpath (e.g., @cyanheads/mcp-ts-core/newutil).
thebrain-ingest
Lay material into TheBrain as a connected graph rather than a pile of notes. Use when asked to "put this article in my brain", "save this", "add it to the knowledge base", "break this down and record it" — about an article, a document, a discussion, a research result or the user's own thinking. Covers: how finely to…
thebrain-organize
Tidy up TheBrain: find duplicates, thoughts with no links, empty stubs, scattered branches about the same thing. Use when asked to "clean up my brain", "find duplicates", "what is dangling with no links", "sort this out", "the structure has drifted". Covers: how to hunt for disorder, what you may fix yourself, and…
thebrain-research
Use TheBrain as a knowledge base when answering a question: look at what is already known first, and only then reason. Use when asked "what do I know about X", "what do I have on this topic", "have we discussed this already", "remind me what we concluded", and before any substantive answer on a topic that might be in…
thebrain-digest
Report what happened in the brain over a period, and what deserves going back to. Use when asked "what did I add this week", "show me a digest", "what have I been working on", "what is new in the brain", and at the start of a session when the context of previous work needs recalling. Covers: how to read the…