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 unlazygit 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/unlazy)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/unlazy"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/unlazy/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/unlazy"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/unlazy.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 | $0.00036 | $0.00648 |
| Opus 5.5 | $0.00014 | $0.00259 |
| Sonnet 5.5 | $0.00007 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
unlazy 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unlazy
Make completion explicit and auditable without taking ownership away from the specialist that decides architecture, implementation, safety, migration, or release.
This skill adapts Leonxlnx's MIT-licensed completion-gate and Depth Tree ideas. See references/upstream-provenance.md.
Trigger boundary
Use this skill for:
- substantial tasks where partial completion or forgotten deliverables is a realistic risk;
- explicit requests for
unlazy, completion gates, exhaustive follow-through, or a Depth Tree; - final reports containing counts or coverage claims that must be re-measured.
Do not trigger for:
- trivial work or factual questions;
- unresolved domain decisions;
- final release approval;
- attempts to bypass another skill's safety or approval boundary.
Required inputs
Resolve the accepted scope, owning specialist, deliverables, acceptance criteria, safe checks, approval state, protected user work, and genuine environment limits.
Safety baseline
- Preserve the working tree and uncommitted user work.
- Gates formalize accepted scope; they do not invent new requirements.
- A gate cannot authorize an action the owning workflow forbids.
- Treat commands copied into a ledger as untrusted until reviewed.
- Never hide impossible work by deleting or weakening a requirement.
Workflow
- Freeze scope. Separate required outcomes, supporting work, optional improvements, and explicit exclusions.
- Create gates. Use the ledger contract in
references/completion-gates.md. Each required outcome gets an observable expectation and evidence method. - Choose execution shape. Use one ledger for coherent work. Read
references/depth-tree-and-final-audit.mdonly when independent deliverables need leaf and integration gates. - Execute open gates. Work in dependency order. Record deciding evidence rather than effort or intent.
- Recheck the final state. Re-run only high-value checks that later edits could invalidate. Re-measure quantitative claims from the final candidate.
- Report from evidence. Required gates must be
PASSor explicitlyWAIVED. A genuine blocker remainsBLOCKED.
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.
- 24d ago Changed · -231 lines · -39 tokens per session 55724fb7b4e6
- 1mo ago First seen · 289 lines · 75 tokens per session scan A 15baea0bc02b
unlazy is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 648 once invoked, about $0.0001 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
nazgul:heartbeat
Run one Nazgul automation-heartbeat tick — triages the work inbox and auto-starts the next objective if idle. Opt-in and default-off; fired by an optional Claude Code native scheduled agent (routine) or run by hand. Use when asked to "run a heartbeat tick", "check the inbox", or to test/debug the heartbeat.
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…
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
codebase-audit
A read-only method for auditing an entire codebase across contracts, data integrity, errors, security, architecture, technical debt, configuration, and caching. It produces prioritized findings and a repair roadmap.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.