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 skills/cmdr-chara/codex-toolkit/codebase-evolution-controllernpx skills add cmdr-chara/codex-toolkit --skill codebase-evolution-controllergit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWhat 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 | $0.00081 | $0.01903 |
| Opus 5 | $0.00041 | $0.00951 |
| Sonnet 5 | $0.00016 | $0.00381 |
| Haiku 4.5 | $0.00008 | $0.00190 |
Grade A, and why
codebase-evolution-controller 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Evolution Controller
Treat evolution as a controlled state transition, not a version-number edit.
Trigger boundary
Use this skill for:
- upgrading a framework, runtime, SDK, compiler, database, or major dependency;
- migrating API, event, storage, serialization, or configuration contracts;
- planning dual-read/dual-write, compatibility adapters, canaries, or phased client transitions;
- removing a deprecated path after measurable exit criteria are met.
Do not trigger for:
- finding why the current system fails—use
debugging-investigatorfirst; - adding a feature that does not change a compatibility boundary;
- package shopping without a concrete repository and decision;
- approving a release—hand integrated evidence to
verification-and-release.
Required inputs
Capture:
- repository state and relevant component/consumer map;
- current state, desired target, business/technical reason, and deadline;
- supported runtimes/platforms and external consumers;
- production data/configuration and deployment topology;
- rollback constraints, maintenance window, and acceptable compatibility period;
- current primary-source evidence for target compatibility and security.
If target state is not specified, compare feasible targets and recommend one with evidence; do not silently choose “latest.”
Safety baseline
- Inspect and preserve uncommitted work.
- Read manifests and lockfiles before proposing commands. Never assume package manager, workspace, or build mode.
- Do not run automatic upgrade, code-mod, formatter, migration, or generator tools without first recording scope, expected changes, version, and rollback.
- Never edit generated outputs without identifying and running the authoritative generator.
- Back up or snapshot production data through the system's established mechanism before irreversible transitions; do not invent a backup command.
- Avoid destructive database or Git commands. Rehearse rollback against representative data where consequence warrants it.
What ships with it
4 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.
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 First seen · 215 lines · 81 tokens per session scan A d18fa62d1a7a
codebase-evolution-controller is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 1,903 once invoked, about $0.0004 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 skills, from other repositories
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
agent-orchestrator-v2
Agent Orchestrator workflow skill. Use this skill when the user needs Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management and the operator should preserve the upstream workflow, copied support files, and…
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.
agent-orchestration-multi-agent-optimize-v2
Multi-Agent Optimization Toolkit workflow skill. Use this skill when the user needs Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability and the operator should preserve the upstream workflow…