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-conflict-mediationgit 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-conflict-mediation)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/culture-conflict-mediation"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/culture-conflict-mediation/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-conflict-mediation"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/culture-conflict-mediation.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 | $0.00039 | $0.01751 |
| Opus 5 | $0.00019 | $0.00875 |
| Sonnet 5 | $0.00008 | $0.00350 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
culture-conflict-mediation 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 conflict mediation
Contract
| Field | Bound contract |
|---|---|
| Trigger | Two colleagues' working friction needs trait-based explanation, accommodations, process changes, and escalation boundaries. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Produces chat output only. |
| Side effect | A trait-gap map, reciprocal perspectives, person-specific accommodations, process changes, conversation guide, and escalation criteria returned in chat. |
| Done | The primary trait-based friction is grounded, both parties receive concrete accommodations, hardwired differences are respected, and non-trait conflicts are excluded or escalated. |
Inputs
Required: two colleagues' Culture Index profiles, each with A/B/C/D trait positions relative to the arrow, archetype/pattern, and EU survey and job values. Required: their working relationship type (peers, manager to report, report to manager, cross-functional, close collaborators, or occasional interaction). Optional: observed friction examples and current date.
Procedure
- Load both profiles. For each person record name, role, archetype, A/B/C/D positions relative to the arrow, and EU survey/job values. Done when: both profiles are recorded with all four trait positions and EU values, or a missing field is named and the stop is reported.
- Screen for non-trait conflicts before mapping any traits. If the conflict involves values, ethics, harassment, or performance issues, stop or escalate it to the appropriate channel and generate no trait-based explanation or accommodation for it. Confirm the remaining friction is explainable by trait differences before proceeding to trait mapping. Done when: any non-trait conflict is stopped or escalated before trait mapping, and the remaining friction is confirmed as trait-based.
- Map trait differences. For each trait A through D, calculate the gap between the two positions and note whether they fall on the same side of the arrow. Traits on opposite sides with large gaps carry the highest friction risk. Done when: all four traits A through D have a computed gap and a same-side or opposite-side determination.
- Identify the primary friction source by matching the largest cross-arrow gaps to known patterns: High A vs Low A (independence vs collaboration), High A vs High A (power struggle), High B vs Low B (social energy mismatch), High C vs Low C (pace mismatch), High D vs Low D (detail orientation), High D vs High D (perfectionism clash). Done when: one friction pattern is named as primary, backed by the specific trait gap from step 3 that produced it.
- Map reciprocal perspectives. For each person, derive how their trait positions likely make them perceive the other: High A sees Low A as indecisive, slow, passive; Low A sees High A as aggressive, selfish, dismissive; High B sees Low B as cold, unfriendly, disconnected; Low B sees High B as chatty, distracting, inefficient; High C sees Low C as chaotic, impatient, disruptive; Low C sees High C as slow, resistant, inflexible; High D sees Low D as sloppy, unreliable, careless; Low D sees High D as rigid, nitpicky, controlling. In a same-trait pair each person reads the other's version of their own trait as its corruption: in High A vs High A, each sees the other's independent action as turf invasion and exclusion from decisions; in High D vs High D, each sees the other's stricter bar as an arbitrary standard that disqualifies their own. Produce both directions. Done when: each person has a perspective list derived from their own trait positions, and both directions are present.
- Assess relationship structure. Peers must find middle ground; in a manager to report pair the manager adapts first because they hold more power; a report to manager mismatch may require environment change if severe; cross-functional priorities compound trait friction; close collaborators accumulate daily friction faster; occasional interaction may permit limiting contact. Done when: the relationship type is named and the power dynamic it creates is stated, so step 7 knows who adapts first.
- Generate reciprocal accommodations specific to the identified friction pair. For High A vs Low A: clarify decision rights, give Low A explicit input time before decisions, Low A understands High A's autonomy is not personal, define consultation points before independent action. For High B vs Low B: acknowledge different social needs, High B reduces social expectations from Low B, Low B commits to brief check-ins, schedule bounded social interaction. For High C vs Low C: acknowledge pace difference as legitimate, Low C gives advance notice of urgent requests, High C accepts some urgency is real and builds buffer time, set deadlines with High C's processing time in mind. For High D vs Low D: acknowledge different detail orientations, High D accepts "good enough" thresholds, Low D agrees to minimum quality gates, define what "done" means for shared work. For High A vs High A: divide decision rights by domain so each person owns the decisions in their area, name which decisions are joint, and bar unilateral moves in the other's domain. For High D vs High D: agree on one shared quality bar per deliverable with a single named setter, and resolve disagreements against the agreed standard rather than by escalating strictness. Done when: each person has at least one accommodation keyed to the primary friction pattern from step 4, and the accommodations are reciprocal rather than one-sided unless the relationship structure from step 6 dictates otherwise.
- Design process changes keyed to the friction source: pace mismatch → define response time expectations and meeting cadence; decision friction → RACI or decision rights matrix; communication style → agree on preferred channels and formats; detail orientation → define quality gates and checklists; social needs → protected focus time vs collaboration time. Done when: at least one process change is proposed for the primary friction source, and each change names the specific friction pattern it addresses.
- Identify what will not change. CI traits are hardwired; name each person's trait-driven behavior that will persist. The goal is accommodation, not transformation. Done when: each person has at least one hardwired behavior named, and the list distinguishes traits from choices so the mediation does not aim at transformation.
- Check energy levels. Compare each person's EU survey against EU job to compute utilization. If either is in stress or frustration, flag that energy drain may intensify natural friction and address workload or role adjustment as part of mediation. Done when: both persons have a utilization classification (engaged, stress, or frustration), and any stress or frustration state is flagged as a friction intensifier.
- Compile the mediation report with: profile comparison table, primary friction source with one-to-two sentence explanation, reciprocal perceptions, person-specific accommodations for each party, process changes, hardwired behaviors that will not change, energy status, a conversation guide framing the discussion as different valid working styles (avoid labeling either style wrong, expecting fundamental change, or assuming one must adapt more unless manager-report), success indicators, and escalation criteria. Done when: the report contains all ten sections, and the conversation guide frames the friction as different valid styles without labeling either party wrong.
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 · +1 lines · -10 tokens per session 7458f2123bf8
- 7d ago First seen · 45 lines · 49 tokens per session scan A efc4f8f669bb
culture-conflict-mediation is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 5d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,751 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
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
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.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.