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 agentmods add skills/davisjam/model-based-agentic-software-engineering/self-governancenpx skills add davisjam/model-based-agentic-software-engineering --skill self-governancegit clone --depth 1 https://github.com/davisjam/model-based-agentic-software-engineeringWhat 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 | $0.00291 | $0.02008 |
| Opus 5 | $0.00146 | $0.01004 |
| Sonnet 5 | $0.00058 | $0.00402 |
| Haiku 4.5 | $0.00029 | $0.00201 |
Grade A, and why
self-governance 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 3d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Governance
This skill applies MAGE to the agent's own engineering work. It carries the modeling repertoire, the engineering moves, the Alignment mechanisms, and the judgment to choose among them — and it composes model providers and other skills to act. It is a router, not a manual: each facet below owns one question, and this file sends you to the right one.
The engineering loop
Everything here supports one loop. Run it whenever you engineer.
recognize the situation
|
what do I need to know?
/ \
MODEL ALIGN
what is missing? what must hold?
\ /
choose an engineering move
|
choose a capability
|
act through the GEE
|
weigh the evidence
/ \
success failure
| |
continue diagnose
|
durable lesson?
/ \
no yes
| |
repair capitalize
MODEL and ALIGN are the two — and only two — MAGE activities. Modeling makes engineering knowledge explicit; Alignment gives that knowledge authority. Self-Governance is not a third activity beside them; it is the discipline of applying both to your own work.
When failure means a generate-evaluate loop is not converging rather than a single action was wrong,
practice/judgment.md ("When search stalls") diagnoses which ingredient — searcher, model, oracle, or
target — is missing before you add more of anything.
What this skill establishes
- Self-Governance applies MAGE to the work. It is the method turned on the agent's own engineering, not a separate practice.
- Modeling and Alignment remain the two activities. Self-Governance is not a third one.
- The skill knows the method; model providers know the system. Concrete system truth —
what this codebase intends, contains, and guarantees — arrives through providers, never
from memory. See
system/model-access.md. - Specialized capabilities come through other skills. Self-Governance chooses the
move; a specialized skill executes it. See
skills/repertoire.md. - Consequential action stays bounded by the GEE. Self-Governance supplies judgment; the governed engineering environment supplies authority. A move becomes consequential only through that environment — never by the skill asserting its own output is safe.
- Self-Governance is not Self-Operate. This skill engineers and improves the environment; it does not run operational lifecycles. When the task is to execute or recover one, cross the boundary to the operate skill.
- Self-Governance is not self-certification. The agent may learn to govern its work; it does not thereby become the authority that certifies that work. Guardrails are proposed and scaffolded, then handed to a human or the harness — never claimed as enforced when only recommended.
What ships with it
60 files 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.
- alignment/mechanisms/ABSTRACTIONS.md 9.1 KB
- alignment/mechanisms/agent/context-and-dispatch/brief-linting.md 7.1 KB
- alignment/mechanisms/agent/context-and-dispatch/docs-hierarchy.md 5.5 KB
- alignment/mechanisms/agent/context-and-dispatch/dynamic-context-injection.md 8.2 KB
- alignment/mechanisms/agent/context-and-dispatch/role-typed-dispatch.md 5.4 KB
- alignment/mechanisms/agent/gates-and-merge-train/merge-train-mis-batching.md 4.3 KB
- alignment/mechanisms/agent/gates-and-merge-train/pre-commit-hook.md 5.3 KB
- alignment/mechanisms/agent/gates-and-merge-train/sentinel-first-commit.md 4.4 KB
- alignment/mechanisms/agent/gates-and-merge-train/staged-deploy-gates.md 4.0 KB
- alignment/mechanisms/agent/governance-doc-controls/claude-md-rule-index.md 8.1 KB
- alignment/mechanisms/agent/governance-doc-controls/doc-hygiene-lints.md 4.2 KB
- alignment/mechanisms/agent/governance-doc-controls/epic-and-design-templates.md 5.8 KB
- alignment/mechanisms/agent/governance-doc-controls/epic-definition-of-done.md 5.2 KB
- alignment/mechanisms/agent/governance-doc-controls/independent-design-review.md 7.9 KB
- alignment/mechanisms/agent/governance-doc-controls/mandatory-snippet-table.md 4.5 KB
- alignment/mechanisms/agent/governance-doc-controls/operational-playbooks.md 5.4 KB
- alignment/mechanisms/agent/governance-doc-controls/operator-runbook-skill.md 8.6 KB
- alignment/mechanisms/agent/governance-doc-controls/self-governance.md 10 KB
- alignment/mechanisms/agent/governance-doc-controls/semantic-level-enforcement.md 10 KB
- alignment/mechanisms/agent/lifecycle-and-observability/agent-registry.md 4.4 KB
- alignment/mechanisms/agent/lifecycle-and-observability/caused-by-provenance.md 7.9 KB
- alignment/mechanisms/agent/lifecycle-and-observability/cron-alerts-gate.md 4.2 KB
- alignment/mechanisms/agent/lifecycle-and-observability/deploy-heartbeats.md 3.5 KB
- alignment/mechanisms/agent/lifecycle-and-observability/lifecycle-hooks.md 11 KB
- alignment/mechanisms/agent/lifecycle-and-observability/reflection-facet-substrate.md 9.2 KB
- alignment/mechanisms/agent/lifecycle-and-observability/tombstone-commits.md 4.2 KB
- alignment/mechanisms/agent/lifecycle-and-observability/typed-event-bus.md 5.6 KB
- alignment/mechanisms/agent/mediators-and-resource-locks/aggregate-compute-protection.md 4.1 KB
- alignment/mechanisms/agent/mediators-and-resource-locks/build-serializer.md 3.9 KB
- alignment/mechanisms/agent/mediators-and-resource-locks/resource-pressure-gating.md 6.9 KB
- alignment/mechanisms/agent/mediators-and-resource-locks/test-serializer.md 4.3 KB
- alignment/mechanisms/agent/README.md 2.3 KB
- alignment/mechanisms/downloads/agent-brief-starter.md 4.4 KB
- alignment/mechanisms/downloads/CLAUDE-starter.md 50 KB
- alignment/mechanisms/downloads/design-doc-template-starter.md 11 KB
- alignment/mechanisms/downloads/EPIC-TEMPLATE-starter.md 13 KB
- alignment/mechanisms/downloads/op-playbook-starter.md 3.1 KB
- alignment/mechanisms/INDEX.md 18 KB
- alignment/mechanisms/models-bridge/README.md 11 KB
- alignment/mechanisms/models-bridge/system-models/agent-first-mbse-harness.md 11 KB
- alignment/mechanisms/models-bridge/system-models/agent-orchestration-model.md 8.7 KB
- alignment/mechanisms/models-bridge/system-models/component-zone-model.md 4.0 KB
- alignment/mechanisms/models-bridge/system-models/composed-state-machine-model.md 8.4 KB
- alignment/mechanisms/models-bridge/system-models/concurrency-contracts.md 4.1 KB
- alignment/mechanisms/models-bridge/system-models/control-coverage-census.md 11 KB
- alignment/mechanisms/models-bridge/system-models/control-substrate-dependency.md 9.1 KB
- alignment/mechanisms/models-bridge/system-models/coverage-model-mapping.md 6.0 KB
- alignment/mechanisms/models-bridge/system-models/data-flow-model.md 7.5 KB
- alignment/mechanisms/models-bridge/system-models/deployment-topology-model.md 3.6 KB
- alignment/mechanisms/models-bridge/system-models/domain-registries.md 4.2 KB
- alignment/mechanisms/models-bridge/system-models/drift-parity-gates.md 4.2 KB
- alignment/mechanisms/models-bridge/system-models/executable-source-of-truth.md 5.5 KB
- alignment/mechanisms/models-bridge/system-models/formal-invariant-verification.md 7.0 KB
- alignment/mechanisms/models-bridge/system-models/governance-graph.md 10 KB
- alignment/mechanisms/models-bridge/system-models/invariant-dag-execution-policy.md 14 KB
- alignment/mechanisms/models-bridge/system-models/journey-criticality-test-placement.md 11 KB
- alignment/mechanisms/models-bridge/system-models/journey-task-closure.md 12 KB
- alignment/mechanisms/models-bridge/system-models/lifecycle-model.md 8.3 KB
- alignment/mechanisms/models-bridge/system-models/meta-model-consumption.md 4.7 KB
- alignment/mechanisms/models-bridge/system-models/model-derived-test-obligation-census.md 8.3 KB
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.
- 3d ago First seen · 162 lines · 291 tokens per session scan A 0c863bb7a13f
self-governance is a skill published in the GitHub repository davisjam/model-based-agentic-software-engineering (18 stars, last pushed 3d ago), licensed MIT. It adds 291 tokens to every session and 2,008 once invoked, about $0.0015 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 2026-08-30.
Other skills, from other repositories
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
link-check
Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.
ralph-specum-requirements
This skill should be used only when the user explicitly asks to use $ralph-specum-requirements, or explicitly asks Ralph Specum in Codex to run the requirements phase.
eval-agent
Run evaluation tests against an agent to assess quality and archetype resistance.