What is origin-evolve-skill?

A workflow for turning recorded session traces into approved updates to the project's managed skills.

Use it to review trace records, propose additions, merges, or retirements, and update managed skills without editing their mirrored source files.

It keeps proposed skill changes evidence-based and ensures every write is approved and placed in the correct skill directory.

origin-evolve-skill — Skill by yunzeforbetter/CastFlow

Install

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.

Any agent

npx skills add yunzeforbetter/CastFlow --skill origin-evolve-skill

Clone the repo

git clone --depth 1 https://github.com/yunzeforbetter/CastFlow

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yunzeforbetter/castflow/origin-evolve-skill/github.svg)](https://agentmods.dev/skills/yunzeforbetter/castflow/origin-evolve-skill)

Your own site

<a href="https://agentmods.dev/skills/yunzeforbetter/castflow/origin-evolve-skill"><img src="https://agentmods.dev/badge/skills/yunzeforbetter/castflow/origin-evolve-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yunzeforbetter/castflow/origin-evolve-skill"><img src="https://agentmods.dev/badge/skills/yunzeforbetter/castflow/origin-evolve-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,227 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Rogue Agent · line 23
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
high Prompt Injection · line 33
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
high Prompt Injection · line 33
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00040	$0.01227
Opus 5.5	$0.00016	$0.00491
Sonnet 5.5	$0.00008	$0.00245
Haiku 4.5	$0.00004	$0.00123

Measured 15d ago against content hash 824c55d14c20, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

origin-evolve-skill scanned grade B with 1 finding 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 15d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Step 3.** Each proposal: Append / Merge / Retire, target skill+file, full text, evidence timestamps + slugs, risk. Proposal sentences use `.castflow-runtime/config.json` `language` (missing or `en` is English, `zh` is

.castflow/core/skills/origin-evolve-skill/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Origin Evolve

Turn pending memory snapshots in .castflow-runtime/traces/trace.md into approved skill updates. A project skill is written under castflow-skills/<name>/, including a later update of that skill. Never write a project skill under .castflow-runtime/skills/ (cold start replaces that tree). Never write a factory-owned skill. Never write adapter mirrors. After writes: python .castflow/manager.py sync.

Trigger: origin evolve (or the same intent). Never run unprompted.

Yield

Install / UI -> castflow.bat / manager.py launch (not a skill)
Create a new module skill -> the pasted /goal prompt (MODULE_MARK_SYSTEM_PROMPT.md)
Requirement to a runnable long task -> goal-loop-creator
Feature work in a module -> that programmer-*-skill

Nav

Need	See
Proposal examples	EXAMPLES.md
Evidence / attribution / ops	SKILL_MEMORY.md
When to edit this skill	ITERATION_GUIDE.md

Trace (schema:4)

Hook-generated ledger. Fields: timestamp, type, validated, quality, gate_hint, memory_snapshots, plus MEMORY subblocks with skill, anchors, quality. Read-only. Ignore legacy score / modules / pipeline_run_id / pending-pipeline.

Eligible (MEMORY grain)

validated does not grant eligibility. It only sorts already-eligible items and counts the TRACE toward notify.

eligible(m) =
  (m.type == feedback AND m.quality == ok)
  OR homologous_count(m) >= 2

homologous_count(m) is the size of m's connected component from python .castflow/manager.py homology (includes self). Singleton size is 1.

Do not invent Jaccard in this skill. Do not spawn one Python process per pair.

Flow

Step 0 Flush if needed -> lock -> Step 1 Triage -> Step 2 Distill -> Step 3 Propose -> Step 4 Approve -> Step 5 Write

Step 0. If .castflow-runtime/traces/.trace_memory_snapshots exists, run python .castflow/manager.py flush before taking .trace_lock. Then create .trace_lock. If the snapshot store still exists, abort (do not call flush while holding the lock).

Read the full file on GitHub · 69 lines

Files

What ships with it

3 files 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.

Changes

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.

15d ago Changed 824c55d14c20
28d ago Changed 714ab65c86e9
1mo ago Changed · -6 tokens per session 8377c7cff28e
1mo ago Changed · -46 lines · +9 tokens per session scan A → B 1ac3d22a78fa
1mo ago First seen · 115 lines · 37 tokens per session scan A a3ad9e23f00c

Subscribe to this mod's changes

origin-evolve-skill is a skill published in the GitHub repository yunzeforbetter/CastFlow (108 stars, last pushed 16d ago), licensed MIT. It adds 40 tokens to every session and 1,227 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

origin-evolve-skill