Borrowing it
Nothing to install: this file belongs to PostHog/wizard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PostHog/wizard/main/.claude/skills/adding-skill-program/SKILL.mdgit clone --depth 1 https://github.com/PostHog/wizardWrote 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/posthog/wizard/adding-skill-program)<a href="https://agentmods.dev/skills/posthog/wizard/adding-skill-program"><img src="https://agentmods.dev/badge/skills/posthog/wizard/adding-skill-program/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/posthog/wizard/adding-skill-program"><img src="https://agentmods.dev/badge/skills/posthog/wizard/adding-skill-program.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 | $0.00044 | $0.02595 |
| Opus 5.5 | $0.00018 | $0.01038 |
| Sonnet 5.5 | $0.00009 | $0.00519 |
| Haiku 4.5 | $0.00004 | $0.00260 |
Grade A, and why
adding-skill-program 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 14d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a Skill-Based Program
Read wizard-development for the shared design policy. Use Pi for new agent work and prefer an orchestrator flow. Linear runs are for very simple work and existing flows. The Anthropic SDK remains a supported legacy fallback, deprecated as the default for new work; the shared guide owns the fallback criteria and gateway model/effort/system-prompt contract.
These are contribution defaults. A program whose config sets no binding runs
on DEFAULT_BINDING, Pi and
linear.
Choose the contribution surface
- Content-only capability: use the existing skill command machinery when it
can express the workflow.
Context-mill owns skill content and
cliEntries. A new skill-backed child of an existing family ships through context-mill; inspect family dispatch. Unpromoted skills run through the skill command. - Native program: use a ProgramConfig when the wizard needs its own flow, screens, detection, composition, or other native behavior. Keep product instructions in context-mill.
Command names, program id, context-mill agentFlow, and skillId have
different roles. Use the full product name for public commands. The config field
is id.
Build a native orchestrator program
Use metrics as the current Pi/orchestrator example and read the runner architecture when changing execution behavior.
- Add the program folder
src/programs/<id>/. Itsindex.tsis the only entry: it exports theProgramConfigasconfig, and any detectors or keys the TUI and CLI need. No other file in the folder is namedindex.ts. Copy a sibling'stsconfig.jsoninto the folder, unchanged, and add{ "path": "<id>" }toreferencesinsrc/programs/tsconfig.json. The folder is one project, its tests included, andpnpm typecheck(tsc -b) builds it. Without the reference, the registry's import fails with TS6307. Keep tests in<id>/__tests__; they reach other layers through their entries only. Shared program code goes insrc/programs/shared/,detection/,warehouse-sources/,frameworks/oroauth/, never in another program's folder, and has noindex.ts. A program imports its own files and the shared program code by relative path, such as../shared/skill-program. SetagentFlowwhen its context-mill flow differs fromid; setting it explicitly also documents the content dependency. Keep arundefinition sorunProgramexecutes agent work. - Supply the flow's seed and task prompts in context-mill, including the task
dependencies and applicable skill variants. The
orchestrator
loads
agentFlow ?? id, requires a seed prompt, and checks task-skill variants before running.run.skillIdalone does not define this flow. - Register the config: import it as
import { config as <name> } from '@programs/<id>'in program-registry.ts and add it toPROGRAM_REGISTRY. Set the config'sbindingto Pi and the orchestrator.ProgramIdis astring. - For a standalone native command, create a command module in
src/cli/commands with
nativeCommandFactory
and register it in
runCliin src/cli/index.ts. A native family child uses the handlers in family dispatch. Program registration derives screen sequences and store lookup, not the top-level CLI.use()chain. - Check the program's OAuth scopes against the tools it needs. Add
oauthScopeAdditionsto the config only when the base set is insufficient. Keep a program's own set in its folder, as replay-vision does; sets several programs share live inprogram-scopes.ts.
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.
- 14d ago Changed · +1 lines d4e7b308c0dc
- 1mo ago Changed · +45 lines 2f7028db18ba
- 1mo ago Changed 1f29b6157cfc
- 1mo ago Changed 16ee0e12460d
- 1mo ago Changed 40b08228d7c4
- 1mo ago Changed · +3 lines 60148c7a522e
- 1mo ago Changed · -20 lines · -29 tokens per session e6c2345f9df6
- 2mo ago First seen · 160 lines · 73 tokens per session scan A 88b8e7557520
adding-skill-program is a skill published in the GitHub repository PostHog/wizard (201 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,595 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 2026-08-30.
adding-skill-program compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adding-skill-programPostHog/wizard | Skill | 201 | yesterday | MIT | A | 44 | Claude Code |
| cep-wizardlinkpranay-ai/context-engineering-protocol | Skill | 10 | 1mo ago | Apache-2.0 | A | 168 | Claude Code, Codex |
| suanfish-design-systemSuanFishXYY/suanfish-design-system | Skill | 8 | 4mo ago | none | A | 293 | Claude Code, Codex |
| analytics-productsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 35 | Claude Code |
| cudaq-guideNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 26 | Claude Code, Codex |
| cudaq-guideNVIDIA/cuda-quantum | Skill | 1.2k | yesterday | Apache-2.0 | A | 26 | Claude Code, Codex |
| hr-onboardingnexu-io/html-anything | Skill | 9.4k | 24d ago | Apache-2.0 | A | 21 | Claude Code, Codex |