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 agentmods add commands/gobing-ai/superskill/magent-evolvegit clone --depth 1 https://github.com/gobing-ai/superskillWrote 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/commands/gobing-ai/superskill/magent-evolve)<a href="https://agentmods.dev/commands/gobing-ai/superskill/magent-evolve"><img src="https://agentmods.dev/badge/commands/gobing-ai/superskill/magent-evolve.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.01071 |
| Opus 5 | $0.00006 | $0.00535 |
| Sonnet 5 | $0.00003 | $0.00214 |
| Haiku 4.5 | $0.00001 | $0.00107 |
Grade A, and why
magent-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 yesterday.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Magent Evolve
Wraps cc:cc-magents skill.
Analyze main agent config quality over time, persist refine-backed proposals, apply deterministic proposals, and inspect or rollback applied versions. Magents are frontmatter-OPTIONAL plain markdown (AGENTS.md/CLAUDE.md/GEMINI.md), so proposals on a frontmatter-less config target the body rather than a frontmatter.description field. Delegates to cc:cc-magents skill.
When to Use
- Print a longitudinal analysis (trend table, score, data sources) without writing a proposal
- Generate proposals after evaluation drift or repeated review feedback
- Apply low-risk fixes through deterministic refine flow with backup and version snapshot
- List applied versions or rollback to a prior version snapshot
Arguments
| Argument | Description | Default |
|---|---|---|
<name> |
Name or path of the config | (required) |
--analyze |
Print analysis summary (trends, score, data sources) without writing a proposal | 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 (e.g. magent-evolve-2026-06-22-001) |
- |
--reject <id> |
Reject a saved proposal | - |
--history |
List applied proposal versions from the store | false |
--rollback <id> |
Rollback to a prior version by proposal_id (requires --confirm) |
- |
--confirm |
Confirm a destructive operation (required for --rollback) |
false |
--json |
Output machine-readable JSON (envelope-out with --propose-only) |
false |
--ingest <file> |
Consume agent-authored proposal JSON (ingest-in mode) | - |
--margin <n> |
Δ-margin gate threshold for accept | 0.05 |
--eval-gate |
Enable the empirical behavior gate when eval cases exist | false |
--target |
Target platform | claude |
Examples
# Print longitudinal analysis (no proposal written)
/cc:magent-evolve AGENTS.md --analyze
# Generate persisted proposals
/cc:magent-evolve AGENTS.md --propose-only
# Apply a proposal
/cc:magent-evolve AGENTS.md --accept magent-evolve-2026-06-22-001
# List applied versions
/cc:magent-evolve AGENTS.md --history
# Rollback to a prior version
/cc:magent-evolve AGENTS.md --rollback magent-evolve-2026-06-22-001 --confirm
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.
- yesterday Changed · +12 lines c7113101811d
- 4d ago First seen · 81 lines · 13 tokens per session scan A ee094bbdd4ea
magent-evolve is a command published in the GitHub repository gobing-ai/superskill (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 1,071 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.