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-burnout-detectiongit 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-burnout-detection)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/culture-burnout-detection"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/culture-burnout-detection/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-burnout-detection"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/culture-burnout-detection.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 | $0.00040 | $0.01661 |
| Opus 5 | $0.00020 | $0.00830 |
| Sonnet 5 | $0.00008 | $0.00332 |
| Haiku 4.5 | $0.00004 | $0.00166 |
Grade A, and why
culture-burnout-detection 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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Culture burnout detection
Contract
| Field | Bound contract |
|---|---|
| Trigger | Survey and Job Culture Index profiles need analysis for stress, frustration, burnout, disengagement, or flight-risk signals. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Chat output only: energy utilization, arrow and trait movement, polarizing shifts, risk level, likely stress sources, and interventions. |
| Done | Energy utilization and every trait movement are calculated, material shifts are flagged, a risk level is assigned by the defined rules, uncertainty is stated, and actionable nonclinical recommendations are produced. |
Inputs
Two Culture Index charts for one person are required: the Survey graph (who they are, hardwired) and the Job graph (who they are trying to be at work, adaptive). For each chart, supply: arrow position (tenths), every trait value A B C D L I (integer 0-10), and the EU value (integer). Trait values may be given as [absolute, relative-to-arrow] tuples; use the relative value for interpretation. State how long the current Job behavior has been sustained if known; mark it unknown otherwise. This skill never extracts values from a PDF by visual estimation and never substitutes a single chart for the pair.
Procedure
- Load both charts. Record arrow position, all trait values (A, B, C, D, L, I), and EU for Survey and for Job. Stop if either chart is missing. Done when: both charts are loaded with all values recorded.
- Calculate energy utilization:
Utilization = (Job EU / Survey EU) x 100. Classify the utilization band: 70-130% Healthy (sustainable), above 130% STRESS (overutilization, burnout risk), below 70% FRUSTRATION (underutilization, flight risk). For above 130%, distinguish good stress (self-induced, caring deeply) from bad stress (too much work or too much behavior modification); both still carry burnout risk after 3-6 months. For below 70%, the work does not fit their traits and flight risk rises if unaddressed. Done when: utilization is calculated and the band is classified. - Compare arrow movement Survey to Job. Arrow shifts right = STRESS (pushing harder than natural). Arrow shifts left = FRUSTRATION (pulling back, disengaging). Unchanged = stable. Done when: arrow direction is recorded.
- Analyze each trait's movement Survey to Job and record the signed change. Interpret raising versus dropping: A raising = needs to drive/lead more (self-induced or required); A dropping = being held back (ask who or what is blocking). B raising = role requires more relationship building; B dropping = role isolates them (demotivating if naturally high B). C raising = more focus/patience required than comfortable; C dropping = more urgency/variety required than comfortable. D raising = expected to be more perfectionist/accountable; D dropping = role allows more flexibility. L raising = trying to be more emotional/open; L dropping = compartmentalizing emotions at work. I raising = trying to be more inventive (traditional approach not working); I dropping = forced into traditional approach when naturally inventive. Done when: every trait's signed change and interpretation is recorded.
- Identify polarizing shifts: any trait dot that moves from one side of the norm to the other. Record the trait, the side it moved from and to, and severity (moderate for a one-side-to-norm shift, severe for a full side-to-opposite-side flip). A polarizing shift is drastic behavior modification and is almost certainly not sustainable. Done when: all polarizing shifts are recorded with severity.
- Check for the opposite-pattern warning: when Job behaviors show the opposite of Survey traits across the board (all dots flipped to the opposite side). This is an imminent flight-risk signal; something must change or the person will leave. Done when: the opposite-pattern check is recorded as present or absent.
- Check D specifically as the most common stress indicator: D raised significantly = expected to be more perfectionist/accountable than natural; D polarizing low to high = the most common source of unsustainable stress. Done when: the D check is recorded.
- Assign risk level using these rules. Evaluate the five inputs in order and assign the highest level any rule triggers:
- CRITICAL: opposite-pattern warning is present, OR utilization is above 160% or below 50%, OR two or more severe polarizing shifts are present.
- HIGH: utilization is above 130% or below 70% AND at least one severe polarizing shift is present, OR utilization is above 130% or below 70% AND the behavior has been sustained 3-6 months or longer, OR three or more moderate polarizing shifts are present.
- MODERATE: utilization is above 130% or below 70% with no polarizing shifts, OR utilization is in the Healthy band (70-130%) AND one or two moderate polarizing shifts are present, OR arrow movement is STRESS or FRUSTRATION with no polarizing shifts.
- LOW: utilization is in the Healthy band (70-130%), arrow is stable, no polarizing shifts, and no opposite-pattern warning. Done when: a risk level is assigned with the triggering rule cited.
- Identify likely stress sources. Job behaviors reflect perception of what the role requires. Sources are their leader (manager expectations and communication), the work itself (actual responsibilities), and coworkers. Ask why they perceive they need to behave this way. Done when: stress sources are identified from the trait evidence.
- Produce the report in the Output format. Recommendations must be actionable and nonclinical, tied to the risk level. Avoid these mistakes: ignoring small EU differences (even 10-15% over 130% matters), focusing only on EU (trait movement matters too), dismissing good stress (self-induced stress still causes burnout), using stale data (Job behaviors should be resurveyed every 6 months), and recommending solutions before understanding the source. Done when: the report is produced with recommendations tied to the risk level.
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.
- 4d ago Changed · -22 tokens per session e60580b2ae29
- 7d ago First seen · 51 lines · 62 tokens per session scan A a886b291446f
culture-burnout-detection is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 5d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,661 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.