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 cmdr-chara/codex-toolkit --skill codebase-improvement-plannergit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWrote 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/cmdr-chara/codex-toolkit/codebase-improvement-planner)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/codebase-improvement-planner"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/codebase-improvement-planner/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/cmdr-chara/codex-toolkit/codebase-improvement-planner"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/codebase-improvement-planner.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00043 | $0.00699 |
| Opus 5.5 | $0.00017 | $0.00280 |
| Sonnet 5.5 | $0.00009 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
codebase-improvement-planner 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 24d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Improvement Planner
Choose the highest-value next improvement from repository evidence, then stop before broad implementation unless the user has already authorized a bounded slice.
Trigger boundary
Use this skill for:
- open-ended "what should we improve next?" requests;
- repository modernization or cleanup without a predefined target;
- balanced improvement backlogs across correctness, architecture, delivery, maintainability, and performance.
Do not trigger for:
- a concrete bug or reproduced failure;
- a defined migration, refactor, performance bottleneck, security review, or platform implementation;
- final release approval.
Required inputs
Resolve the repository root, working-tree state, user goal, protected contracts, generated/vendor boundaries, available verification evidence, and whether implementation is already authorized. If business priorities are unknown, rank from technical evidence without inventing product value.
Safety baseline
- Preserve uncommitted user work and start read-only.
- Do not install, upgrade, regenerate, delete, rename, or broadly rewrite merely to discover candidates.
- Treat volatile dependency, runtime, security, and platform claims as unverified until checked against current primary sources.
- Do not edit generated output before identifying its authoritative generator.
Workflow
- Frame the decision. Record scope, desired outcomes, constraints, exclusions, and evidence limits.
- Map the baseline. Inspect structure, contracts, tests/CI, error handling, operational boundaries, and concentrated change/risk areas. Use
repository-intelligencefirst when ownership or blast radius is too uncertain. - Admit candidates. Require a concrete signal: failing/weak evidence, repeated cost, risky coupling, unsupported dependency, missing critical verification, or demonstrable delivery friction. Do not turn style preferences into findings.
- Rank candidates. Apply
references/improvement-ranking.md. Keep change magnitude separate from priority. - Select the next upgrade. State the evidence, expected value, scope, risk, reversibility, verification method, and owning specialist.
- Stop or execute. Without prior authorization, return the backlog and mark the selected item
AWAITING_APPROVAL. With explicit authorization, execute only the selected bounded maintenance slice or hand it to the specialist that owns the concrete task.
What ships with it
2 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.
- 24d ago Changed · -218 lines · -69 tokens per session 33261d51530e
- 1mo ago First seen · 278 lines · 112 tokens per session scan A 559408bd8bfd
codebase-improvement-planner is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 43 tokens to every session and 699 once invoked, about $0.0002 per session on Opus 5.5. 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
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
code-coherence-review
Reviews code and plans for logic coherence, correctness, and structural integrity.