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/unlazynpx 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.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 | $0.00075 | $0.02740 |
| Opus 5 | $0.00037 | $0.01370 |
| Sonnet 5 | $0.00015 | $0.00548 |
| Haiku 4.5 | $0.00007 | $0.00274 |
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 5d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unlazy
Use this skill to make completion an explicit, testable contract instead of a feeling. It is a cross-cutting execution discipline: the specialist skill still owns architecture, debugging, migration, design, implementation, or release decisions; unlazy owns the definition of done, the completion ledger, and the final claim audit.
This toolkit adaptation is based on Leonxlnx's MIT-licensed unlazy method, especially its Depth Tree and gate-ledger ideas. Read references/completion-gates.md for the ledger contract and references/upstream-provenance.md for the exact inspected revision and adaptation boundaries.
Trigger boundary
Use this skill for substantial work when one or more of these are true:
- the user says to finish all requested items rather than sample or partially implement them;
- a task has repeatedly returned half-complete or with premature "done" reports;
- the task is long enough that scope drift or forgotten acceptance criteria are realistic;
- the user explicitly asks for
$unlazy, "unlazy", a depth tree, completion gates, or equivalent completion discipline; - the final report contains counts, coverage claims, file totals, or other measurable statements that must be re-measured rather than recalled;
- several independent deliverables need their own verification before integration can be called complete.
Do not trigger for:
- conversational replies, translations, simple factual lookups, or one-line edits;
- ordinary implementation where the existing specialist's acceptance criteria are already small and directly verifiable;
- tasks whose main decision is still unknown, such as root-cause diagnosis, platform selection, product direction, or release approval—the owning specialist remains primary;
- requests to bypass safety controls, erase evidence of incomplete work, or convert an explicit blocker into a success state;
- extra work invented merely to make the task larger.
unlazy may be used alongside a specialist. It does not grant permission to cross that specialist's stop condition.
What ships with it
3 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.
- 5d 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 7d ago), licensed MIT. It adds 75 tokens to every session and 2,740 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-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
pause
Stops current work on user request, captures full session state to project docs, and generates a resume prompt so the next session can continue without loss. Use when: "пауза", "стоп", "остановись", "stop", "pause", "подожди", "притормози", "сохрани прогресс", "прервись", "halt".
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
oma-recap
Analyze conversation histories from multiple AI tools (Grok, Claude, Codex, Gemini, Qwen, Cursor, Antigravity) and generate themed daily/period work summaries. Filter by date or time window.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
obsidian-kb-artifacts
Use this skill for Obsidian-native formatting and derived artifacts such as Markdown formatting, wikilinks, registry tables, canvas files, optional Bases, CLI operations, and link repair. This skill does not decide knowledge routing.