skill-evolve

A command for studying how a coding-agent skill changes over time and managing proposed improvements.

In plain words
What is it for?
Use it to analyze evaluation trends, draft or apply improvement proposals, reject proposals, view history, or roll back a version.
Why use it?
It helps identify declining or consistently weak areas while keeping a record of accepted versions and backups.

Command

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.

agentmods
npx agentmods add commands/gobing-ai/superskill/skill-evolve
Clone the repo
git clone --depth 1 https://github.com/gobing-ai/superskill
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.00942
Opus 5 $0.00006 $0.00471
Sonnet 5 $0.00003 $0.00188
Haiku 4.5 $0.00001 $0.00094

Measured 2d ago against content hash 7ee887d28c20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-evolve 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 2d 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.

Origin

This is a copy

86% identical to agent-evolve — 33 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/cc/commands/skill-evolve.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Evolve

Wraps cc:cc-skills skill.

Analyze skill quality over time, draft heuristic proposals for declining/flat-low dimensions, apply proposals through the double-loop gate, and rollback to prior versions via saved snapshots. Delegates to cc:cc-skills skill.

When to Use

  • Analyze trends, data sources, and patterns without writing a proposal (--analyze)
  • Generate proposals after evaluation drift or repeated review feedback (--propose-only)
  • Apply proposals through the deterministic double-loop gate with backup and rollback (--accept, --rollback)
  • Track applied versions over time (--history)

Arguments

Argument Description Default
<name> Name of the skill (dir name or path to SKILL.md) (required)
--analyze Print trend table, score/grade, data-source inventory, and pattern summary false
--from <date> Analyze evaluations since date (ISO 8601) latest
--propose-only Draft proposals without applying false
--accept <id> Apply a saved proposal by ID -
--reject <id> Reject a saved proposal by ID -
--history List applied proposal versions from the store false
--rollback <id> Restore a prior version by proposal_id (requires --confirm) -
--confirm Confirm a destructive operation (required for --rollback) false
--ingest <file> Agent-authored proposal JSON (ingest-in mode) -
--json Output machine-readable JSON (envelope-out with --propose-only) false
--margin <n> Δ-margin gate threshold for accept (default 0.05) 0.05
--eval-gate Enable the empirical behavior gate when eval cases exist false
--target Target platform claude

Examples

# Generate persisted proposals
/cc:skill-evolve ./skills/my-skill/SKILL.md --propose-only
# Analyze trends without writing a proposal
/cc:skill-evolve ./skills/my-skill/SKILL.md --analyze
# Apply a proposal
/cc:skill-evolve ./skills/my-skill/SKILL.md --accept skill-evolve-2026-06-22-001
# List applied versions
/cc:skill-evolve ./skills/my-skill/SKILL.md --history
# Rollback to a prior version
/cc:skill-evolve ./skills/my-skill/SKILL.md --rollback skill-evolve-2026-06-22-001 --confirm

Read the full file on GitHub · 82 lines

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.

  1. 2d ago First seen · 82 lines · 13 tokens per session scan A 7ee887d28c20

Subscribe to this mod's changes

skill-evolve is a command published in the GitHub repository gobing-ai/superskill (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 13 tokens to every session and 942 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to agent-evolve, differing in 33 lines, and is treated as a copy.