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 tdwhere123/do-it --skill do-it-skill-authoringgit clone --depth 1 https://github.com/tdwhere123/do-itWrote 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/tdwhere123/do-it/do-it-skill-authoring)<a href="https://agentmods.dev/skills/tdwhere123/do-it/do-it-skill-authoring"><img src="https://agentmods.dev/badge/skills/tdwhere123/do-it/do-it-skill-authoring/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/tdwhere123/do-it/do-it-skill-authoring"><img src="https://agentmods.dev/badge/skills/tdwhere123/do-it/do-it-skill-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00650 |
| Opus 5.5 | $0.00014 | $0.00260 |
| Sonnet 5.5 | $0.00007 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
do-it-skill-authoring 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 12d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring
Start from an observed failure or repeated rediscovery, not an imagined need.
Capture it as a reproducible behavior scenario (in this repository,
evals/behavior/) and compare the revision against the current skill, or no
skill for a new one. Write the least guidance that changes the observed
behavior. A scenario that passes with and without the change does not show
the skill helps.
Description
The description decides whether the skill loads. Lead with the situations and symptoms that call for this judgment, and distinguish near-miss tasks that do not need it. Do not summarize the procedure: a model can follow a summarized description instead of reading the body. Check the wording against realistic prompts that should trigger the skill and near misses that should not.
Body
Give the model what it would not do well unaided: distinctive questions, distinctions, counterexamples, tool pitfalls, and precise ownership, permission, and side-effect boundaries. Explain why a constraint exists instead of escalating its emphasis. Match specificity to fragility: judgment stays open, while fragile or irreversible operations deserve exact commands or scripts. Deterministic checks belong in scripts, validators, or hooks rather than prose.
Put load-bearing guidance first; hosts may retain only the opening of a long skill after context compaction. Use one term per concept. Do not repeat Core or another skill's guidance; link its owner with a concrete loading condition. Keep references one level from SKILL.md, and give a long reference a short contents list so a partial read still shows its scope.
Describe what complete work must establish and let the model choose methods and sequence. Do not recreate task tiers, compulsory phase chains, worker or review quotas, stop-status taxonomies, mandatory reports, anti-rationalization tables, or a fixed skill anatomy.
Delegation guidance
When a skill recommends independent contexts, say what independence adds: fresh evidence, an unanchored challenge, a specialist lens with a concrete question, or separable work that benefits from parallel inspection. Also say when it adds nothing: one reader can hold the scope, several lenses apply to the same slice, or splitting would break a chain that one reader should follow end to end. Perspectives are questions, not headcount; one delegate can carry several. Separate source facts and settled decisions from parent hypotheses, name write scopes, and leave integration and verification with the parent.
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.
- 12d ago Changed · +32 lines · +6 tokens per session f0a336e1e208
- 16d ago Changed · +2 lines c008c96fe8a8
- 1mo ago Changed · -188 lines · -6 tokens per session 1e7c023303ac
- 1mo ago Changed · +39 lines e07662924cc6
- 1mo ago First seen · 178 lines · 36 tokens per session scan A c337619ff540
do-it-skill-authoring is a skill published in the GitHub repository tdwhere123/do-it (28 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 650 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 2026-08-30.
Other skills, from other repositories
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.
kirby-headless-api
Exposes Kirby content to headless clients using the API, KQL, and JSON representations. Use when building API endpoints, KQL queries, or headless frontends.
kirby-ide-support
Improves IDE autocomplete and static analysis in Kirby projects with PHPDoc hints and Kirby IDE helper generation. Use when types are missing or IDE support is degraded.
rn-feature-development
This skill should be used when building any new feature in a React Native or Expo app, or when the $rn-dev-agent:rn-feature-dev command runs. Triggers on "build a feature", "add X to the app", "implement Y", "create a new screen", "rn-feature-dev", "feature development", "build me X", "add a screen", "wire up this…
creating-actions
This skill should be used when the user asks to "create an action", "save this flow as an action", "make this replayable", "record a reusable action", "author a Maestro flow as an action", "add a login/setup action", or when a verified UI walk should be persisted under .rn-agent/actions/ so future sessions can replay…
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…