Borrowing it
Nothing to install: this file belongs to frenzymath/Danus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frenzymath/Danus/codex/.agents/skills/elaboration/SKILL.mdgit clone --depth 1 https://github.com/frenzymath/DanusWrote 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/frenzymath/danus/elaboration)<a href="https://agentmods.dev/skills/frenzymath/danus/elaboration"><img src="https://agentmods.dev/badge/skills/frenzymath/danus/elaboration/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/frenzymath/danus/elaboration"><img src="https://agentmods.dev/badge/skills/frenzymath/danus/elaboration.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 | $0.00030 | $0.03383 |
| Opus 5.5 | $0.00012 | $0.01353 |
| Sonnet 5.5 | $0.00006 | $0.00677 |
| Haiku 4.5 | $0.00003 | $0.00338 |
Grade A, and why
elaboration 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elaboration
You are the main agent. At each strategic cycle, including the global review
on each roughly 30-minute heartbeat, you distill the project's current state into
one elaboration when the synthesis materially changes: a readable, deeply
analytical synthesis for your own reasoning and worker dispatch. The heartbeat
itself always requires a fresh global appraisal, but it need not create a
duplicate elaboration when nothing material changed. You may ask speculative
Codex subagents to explore individual gaps or undertake sustained technical
reasoning, but their reports remain unverified and must be labelled as
hypotheses. You author the next master_guidance yourself.
The elaboration is also what you draw on to keep the operator informed.
Template invariants (validate every elaboration against these)
A well-formed elaboration satisfies all of the following — a worker or linter can check them mechanically:
- Five sections, in order, no dropped heading: §0 Mathematical verdict · §1 Closed components and obsolete routes · §2 Interface contract table · §3 Dangerous heuristic lines and strategies not to pursue · §4 Missing bridge lemmas. An empty section is written as its honest empty-state line, never omitted.
- The two fixed empty-state lines (§1) are used verbatim when a subsection is
empty:
_(no signed-closed components yet)__(no failed or obsolete routes recorded; absence here does not mean the strategy is unique)_
- Exactly seven status labels, UPPERCASE, drawn only from: CLOSED · SUBSTANTIAL · PARTIAL · DANGEROUS · FALSE AS STATED · OBSOLETE · UNKNOWN.
- §0 opens with exactly one bolded verdict line and contains the status dashboard table + the sub-task status summary table + the approach portfolio + the Current best proof skeleton + the Central missing lemma.
- Every
fact_idcited exists in the fact graph; no invented ids, no paraphrase substituted for a verified statement. - Published via
gm_add(kind="elaboration", …)withverifiableleft at its default (false).
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 · 253 lines · 30 tokens per session scan A fb0fe75328f3
elaboration is a skill published in the GitHub repository frenzymath/Danus (490 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,383 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
knowledge_store_skill
Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is directory-scoped. Each directory that contains a .knowledge.yaml file…
memory-fabric
Memory retrieval internals: knowledge graph orchestration with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting over unified recency, relevance, and authority ranking. Use when designing or debugging how memory search itself works. Everyday lookups belong…
remember
Write-side memory: stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Use when something worth persisting across sessions was just learned or decided. To search or read existing memory, invoke memory; to debug retrieval internals…
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
memory
Read-side memory operations on the knowledge graph: search past decisions and patterns, load session context, view decision timelines, render Mermaid graph visualizations. Subcommands: search, load, history, viz, status. Use when finding or reviewing what memory already holds. For storing new knowledge instead, invoke…
pod-checkpoint
Write a structured recovery snapshot to lifecycle/checkpoint.md before context reset — captures phase, stage, decisions, and pending items so $pod resume can restore precise context.