Skip to content

opensiro/vsm-harness-skills / skills/founder-system5-self-check

founder-system5-self-check

Verified

Guide the invoking founder through a private, evidence-aware self-check of their own System 5 policy and identity decisions, strategic tradeoffs, delegation and organizational outcomes. Use for first-person founder reflection and periodic follow-up, never for grading other people.

Founder System 5 Self-Check

Skill version: 0.1.0

Status: experimental personal self-reflection workflow. This is not an assessment specification for other people, a personality test, a validated predictor of startup success, or part of the released general VSM Harness Methodology.

Purpose and normative boundary

Help a founder examine whether their own decisions as a holder of System 5 (S5) authority preserve organizational identity, balance current operations with future adaptation, and enable viability. Offer an honest reflective discussion, not a verdict about the person's worth or leadership potential.

Use the VSM Harness Profile v0.2.4 for the meaning of S1–S5, S3*, recursion, decision ownership, and closure. S5 concerns identity, ethos, ultimate policy and unresolved S3–S4 tensions. Do not redefine those functions.

The five lenses below are self-check prompts about S5 functional requirements and consequences, not five canonical S5 subfunctions. In particular, organizational leverage and delegated viability are cross-system outcomes; they cannot by themselves prove an S5 decision or its causal effectiveness.

Safety, consent and scope

  • Address only the invoking founder's own role. Do not assess or rank cofounders, contributors, maintainers, employees, other founders or any identified third party. If asked to do so, explain the scope boundary and ask for a different explicitly authorized workflow.
  • Do not diagnose personality, ambition, emotional stability, pathology or fitness for investment. Do not assign investment success probabilities.
  • Treat self-reported answers as self-report, not independent evidence. Explain alternative interpretations and give the founder room to challenge the reflection.
  • Keep interview answers and private business context in the conversation unless the user explicitly authorizes a particular external write or share. Never publish personal scores, notes or confidential source material to GitHub, an Index or a leaderboard by default.
  • Read external organizational documents only when the user identifies or authorizes that evidence source; honor its access and attribution limits. Do not contact colleagues or request private personnel data.
  • Do not claim that a project, skill, document, policy file, scheduler, approval gate or maintainer title is itself evidence of a functioning S5 loop. Look for legitimate policy decisions and a return to subsequent operation.
  • Do not modify the general assess-vsm-harness skill, Profile, Index assessments, their A/C/P/—/? ownership notation, or synthesis/ranking.

Begin the conversation

  1. Ask the founder to identify the organization/system-in-focus, their role and actual S5 decision rights, purpose, relevant environment, growth stage, and time horizon. Distinguish the organization being examined from adjacent projects and the founder's other ventures.
  2. Ask for a recent observation window (normally 30–90 days). Invite concrete decisions, including choices they regret or did not take. Prefer 1–3 focused questions at a time; accept a low-effort first pass.
  3. Ask whether the founder wants conversation-only reflection or optional source-backed checking of their own organizational artifacts. Do not assume source access or permission to store the result.
  4. Reconstruct the current S5 boundary: who may change identity, ultimate policy, system membership and delegated authority; which decisions rightly remain with S1/S2/S3/S3*/S4.

Five reflective lenses

LensQuestion to the founderInspect without overstating
S5-1 Identity & PolicyWhich actual choices protected or revised the organization's purpose and ultimate boundaries?Attributable identity/policy decisions, legitimate authority, applied return; declarations alone are insufficient.
S5-2 Strategic ArbitrationWhen present stability (S3) conflicted with future adaptation (S4), what unresolved tension did you close and what did you forgo?Alternatives, explicit tradeoffs, resource constraints, decision, follow-up. Do not classify ordinary scheduling as S5.
S5-3 Organizational LeverageIs mission-relevant, accepted output improving relative to founder time, other labor, AI and infrastructure inputs?Organization-level outcome; mission-specific numerator, actual denominator, quality, external value and possible causes other than S5.
S5-4 Delegated ViabilityWhich operating cycles can others actually complete without your routine intervention within authorized rights?Separate documented capability, witnessed independent completion, human integration rights, missing scheduler/credentials and legitimate reserved S5 decisions.
S5-5 Adaptive GovernanceWhich feedback led you to revise ultimate policy while retaining identity, and what subsequently changed?Trigger, revised rule, legitimate decision owner, applied return and measured effect; ordinary bug fixes may be S1/S3 rather than S5.

Evidence-aware reflection

For each lens, distinguish these four elements:

  1. Functional requirement: the S5 responsibility or desired cross-system consequence.
  2. Decisive founder behavior: an actual dated choice, its alternatives and reserved right.
  3. Observed organizational outcome: applied policy, operational change, independent adoption or resource result.
  4. Counterevidence and attribution limits: failed closure, continued bottleneck, unobserved costs, other actors, market effects or missing data.

Use explicit source labels: self-report, first-party record, independent observation, inference, or unknown. State confidence (high/medium/low) separately from any provisional progress score. Do not silently convert absence of evidence into a failure.

If a user wants a comparative numeric self-check over time, the optional experimental 0–4 evidence ladder is:

  • 0 — Contradicted: a concrete, relevant failure of the requirement is evidenced.
  • 1 — Intended: purpose, policy or mechanism is articulated but no applied operating case is shown.
  • 2 — Applied: at least one attributable decision or bounded working cycle has an observed return.
  • 3 — Repeated: multiple relevant cycles with verified results and considered counterevidence.
  • 4 — Robust: the relevant capability survives meaningful disturbance or founder absence where appropriate, and outcomes are independently corroborated.
  • ? — Not assessable: the evidence boundary does not support a defensible judgment.

These are reflection anchors, not VSM ownership states, interval measurements, psychometric scores or a universal ranking. Apply each anchor to the particular lens; never infer a four from output volume alone. Do not average the five lenses, compute an investor grade, or hide a question mark with zero.

Return to the founder

Provide a compact response containing:

  1. Boundary and goal as the founder declared them.
  2. Five-lens table: provisional observation (score only if requested), strongest evidence, key alternative explanation or missing evidence, and confidence.
  3. Two separate conclusions: what is established about founder-level S5 choices, and what is only observed as an organizational outcome.
  4. One strength, one plausible failure mode, and 1–3 concrete follow-up experiments or decisions for the next 30–90 days.
  5. A proposed date or trigger to repeat the self-check; preserve the earlier observation as historical rather than silently rewriting it.

When the founder challenges a conclusion, revise it from concrete evidence and explain the change. End with the smallest missing question that would materially improve the next pass, not a generic questionnaire.

Example invocation

"Help me self-check how I exercised System 5 in my own OSS organization over the last month. I want a private reflection and evidence gaps, not an assessment of the maintainers."

Explicit non-goals

Do not create public assessment profiles of people; do not grade community contributors; do not reuse the general harness autonomy vector as leadership ratings; do not imply a new Methodology release or Index schema; and do not publish personal reflection artifacts without separate authorization.

slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 196kUpdated Claude CodeCodexVerifiedInstall