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 OutlineDriven/outline-driven-development --skill culture-onboarding-plangit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/culture-onboarding-plan)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/culture-onboarding-plan"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/culture-onboarding-plan/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/outlinedriven/outline-driven-development/culture-onboarding-plan"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/culture-onboarding-plan.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 | $0.00037 | $0.00934 |
| Opus 5 | $0.00018 | $0.00467 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
culture-onboarding-plan 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Culture onboarding plan
Contract
| Field | Bound contract |
|---|---|
| Trigger | A signed new hire's actual Culture Index profile and team profiles need translation into a personalized first-90-days plan. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. All output is chat only. |
| Side effect | Chat output only: buddy choice, ally and friction map, manager briefing, communication preferences, 30/60/90-day actions, and success indicators. |
| Done | The plan accounts for the actual profile, team and manager fit, names specific milestones and mitigations, and avoids one-size-fits-all treatment. |
Inputs
Required:
- The signed new hire's actual Culture Index profile: primary trait scores, secondary trait scores, and identified archetype. A generic or placeholder profile is not acceptable.
- Team profiles: each teammate's archetype and trait scores, the team composition, and the hiring manager's profile.
Optional:
- Existing onboarding checklist or role expectations, used only to anchor milestones to real deliverables.
Procedure
- Collect the signed new hire's actual Culture Index profile (primary and secondary trait scores, archetype) and the team profiles (each teammate's archetype and traits, team composition, and the hiring manager's profile). Stop and request the missing or actual assessed profile if any is absent or generic. Done when: the hire's profile and all team profiles are present and actual, not generic.
- Determine the new hire's dominant primary and secondary traits and archetype from the profile; note the motivators and conversation starters that fit those traits. Done when: dominant traits, archetype, motivators, and conversation starters are recorded.
- Map the new hire against the team composition: identify allies (complementary archetypes), friction points (conflicting traits or duplicate role coverage), and gaps the hire fills. Done when: allies, friction points, and gaps are each named with the specific teammates or traits involved.
- Select a buddy whose archetype and traits complement the hire's and who models the team's operating norms; name a specific person, or state the archetype criteria when the person is not yet chosen. Done when: a buddy is named or the archetype criteria for selection are stated.
- Draft a manager briefing covering the hire's motivators, communication preferences, expected friction, and how the manager should adjust their style for this profile. Done when: the briefing covers motivators, communication, friction, and manager style adjustments.
- Set communication preferences derived from the hire's traits: directness level, detail level, and feedback cadence. Done when: directness, detail level, and feedback cadence are each set from the hire's traits.
- Build 30/60/90-day actions as specific milestones tied to the hire's archetype and team fit, with a named mitigation for each friction point from step 3. Done when: each 30/60/90 milestone is specific to the hire's profile and each friction point has a mitigation.
- Define success indicators measurable against the milestones and the hire's motivators; reject generic checklists that do not reference the actual profile. Done when: every success indicator is measurable and references the actual profile.
- Return the plan as chat output. Flag any section that would default to one-size-fits-all treatment as incomplete rather than filling it with boilerplate. Done when: every section cites the actual profile or is flagged incomplete.
What ships with it
1 file 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 Changed · -25 tokens per session aa0c277fd72e
- 7d ago First seen · 46 lines · 62 tokens per session scan A aa38d89305f0
culture-onboarding-plan is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 5d ago), licensed Apache-2.0. It adds 37 tokens to every session and 934 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via /askme.
slicing-code-context
Use when an exact symbol, path, entrypoint, or line range can bound a focused code question or patch proposal under a fixed source budget. Not for source changes or broad repository exploration.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
autopilot
Run a hands-off plan-to-ship pipeline by chaining existing skills. Use when the user says "autopilot", "take this from plan to shipped", "run the whole pipeline", "hands-off ship it", or "do the end-to-end build".
llm-self-loop
Use when a button click, dashboard check, or human verdict sits inside an iteration loop. Replaces it with an autonomous gate or moves non-automatable work outside the loop. Don't use for remote, credential, publish, deploy, or irreversible changes.
catchup
Use when the human returns after a gap, cannot follow the project, asks what happened, or wants a visual HTML recap page. Not for onboarding: use onboard. Not for handoff: use handoff.