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 terrylica/cc-skills --skill d-emergent-resurrectiongit clone --depth 1 https://github.com/terrylica/cc-skillsWrote 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/terrylica/cc-skills/d-emergent-resurrection)<a href="https://agentmods.dev/skills/terrylica/cc-skills/d-emergent-resurrection"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/d-emergent-resurrection/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/terrylica/cc-skills/d-emergent-resurrection"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/d-emergent-resurrection.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 | $0.00031 | $0.02145 |
| Opus 5 | $0.00015 | $0.01073 |
| Sonnet 5 | $0.00006 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00215 |
Grade A, and why
crucible-emergent-resurrection 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 11d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Emergent Resurrection — negative-knowledge archive
Self-Evolving Skill: If the failure taxonomy misses a mode, or a resurrection trigger type recurs, update the relevant section AND append to
references/evolution-log.md. Don't defer.
Failed hypotheses are not waste. They are negative knowledge that:
- Documents the investigation's boundaries
- Prevents re-exploring known dead ends
- Can come back when conditions change
This skill is the genetic-evolutionary mechanism for "don't rule out anything we have tried, as long as it can emerge through iterative process".
Why NOT just delete failed ideas
The session accumulated 17 null campaigns. Without negative-knowledge capture, we would:
- Re-explore the same dead ends in future sessions (wasted compute)
- Lose the meta-lesson each failure taught (wrong null, wrong scaling, wrong scope)
- Be unable to detect when conditions have shifted enough to retry
Failed attempts are cheaper to preserve than to re-run.
Failure-mode taxonomy
Each failed campaign fits one or more modes. Classification determines resurrection conditions.
| Failure mode | Description | Resurrection trigger |
|---|---|---|
null-insignificant |
Signal exists but below noise floor | Noise floor drops (longer backtest, better data, reduced cost) |
overfit-in-sample |
Strong IS, poor OOS | Cross-validation success on a different data regime or architectural redesign |
wrong-null-applied |
Correct signal, wrong null type broke it | Correct null method discovered (see Skill B §5 orthogonal cascade) |
cross-asset-failed |
Works on one asset, breaks on others | Same config trial on a DIFFERENT asset passing, OR regime detector enabling per-asset selection |
regime-conditional |
Full-history fails; edge concentrated in specific regime | Causal walk-forward regime classification + train/test both positive within regime + null z>3 |
label-leaked |
Features/labels violated causality | Causality re-verified (bars[:i] exclusive) and retest OK |
agent-overestimation |
Agent's estimate > reality | External oracle or per-bar replay validates a scaled-down version |
grid-degenerate |
Parameter grid too narrow | Widen grid, OR sensitivity analysis reveals dormant dimension |
dormant-low-precedence |
Valid but lower priority | Higher-priority frontier cleared, revisit |
falsified-comprehensive |
Tested exhaustively; impossible under stated assumptions | Assumptions change (new asset class, new microstructure, regime shift) |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 219 lines · 31 tokens per session scan A 352a9bc439c1
crucible-emergent-resurrection is a skill published in the GitHub repository terrylica/cc-skills (72 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 2,145 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.
customer-persona-builder
Data-driven customer persona development combining market research, user behavior analysis, and segmentation frameworks. Use when creating buyer personas, ideal customer profiles (ICPs), or user archetypes.
devops-cloud
DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.
generic-design-system
Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.
generic-code-reviewer
Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.