self-operations

A set of operating instructions for running a repository that contains multiple software agents and the systems around them. It covers agents, context windows, Git, deployments, the development machine, scheduled jobs, and orchestration hooks.

In plain words
What is it for?
Use it to start or maintain the agent fleet, inspect the repository and deployment lifecycle, diagnose operational symptoms, and find the relevant runbook when something breaks.
Why use it?
It helps you operate the repository from a known healthy baseline and route failures to the right troubleshooting guidance. Recurring failures can be passed to a separate hardening process.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/davisjam/model-based-agentic-software-engineering/self-operations
Any agent
npx skills add davisjam/model-based-agentic-software-engineering --skill self-operations
Clone the repo
git clone --depth 1 https://github.com/davisjam/model-based-agentic-software-engineering

Made for: Claude Code, Codex.

Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00196 $0.04083
Opus 5 $0.00098 $0.02041
Sonnet 5 $0.00039 $0.00817
Haiku 4.5 $0.00020 $0.00408

Measured 2d ago against content hash 14a77aa61e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-operations 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 2d ago.

The scan reads SKILL.md. This mod also ships 15 executable files (hooks/_claude_hook_output_schema.py, hooks/_hook_harness.py, hooks/_hook_registry.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugin/mage/skills/self-operations/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

self-operations — run the repo like a DevOps engineer

You are operating the way the work is done in this repository — the agent fleet and the substrate that produces it. Your job is a DevOps engineer's: keep it running, know how it works, improve it when you touch it. This is the operate half of the pair; self-governance is the harden half. Operate routes a break to its fix; when a failure recurs, hand it to self-governance. The two are two lenses on one substrate, not competitors: self-governance is the design-time census of controls (what exists, what's missing, how to mint one); this skill is their run-time operation. A mechanism lives in that census and is run here — the same thing seen design-time vs run-time.

Read principles.md — the portable operating mindset (positive-first, route-to-class, observability-first RCA, typed runbooks, semantic-gap placement, freedom-to-improve). The rest of this skill is the map you operate against and the bootstrap that fits it to this repo.

How to use this skill

  1. Orient positive first. Read the lifecycle map below — know the healthy baseline before you hunt a break. Most sessions are steady-state operation.
  2. When something breaks, find the symptom's class in your Part B catalog (match the class, not the example that seeded the row), follow its resolving doc, and run the matching runbook's typed steps.
  3. If the cause is unknown, RCA observability-first (principles.md A.3) — an observability gap is itself the first finding.
  4. After resolving, if this failure has happened more than once, run the partner self-governance skill (interpret-failure mode) to classify the class and design the control — a registered, designed control, never an inline hack. Governance is design.

The core lifecycles (the map — know normal before you hunt a break)

Every agent-fleet repo manages the same five core lifecycles (plus cron/scheduling and the operator's own hooks where present). The structure is shared; only the bindings differ (your Part B).

Read the full file on GitHub · 239 lines

Files

What ships with it

39 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.

Changes

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.

  1. 2d ago First seen · 239 lines · 196 tokens per session scan A 14a77aa61e74

Subscribe to this mod's changes

self-operations is a skill published in the GitHub repository davisjam/model-based-agentic-software-engineering (18 stars, last pushed 2d ago), licensed MIT. It adds 196 tokens to every session and 4,083 once invoked, about $0.0010 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.

Related

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…

modu-ai/moai-adk · 98 tokens

kelos

Author, debug, and operate Kelos resources (Task, Session, Workspace, AgentConfig, TaskSpawner) on Kubernetes. Use for Kelos CRDs, resource manifests, the kelos CLI, or live cluster operations. Do not use for ordinary Kelos repo code edits, tests, reviews, build/CI, or git tasks unless they involve those resources.

kelos-dev/kelos · 76 tokens

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…

mindfold-ai/Trellis · 65 tokens

link-check

Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.

jmagly/aiwg · 29 tokens

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.

tzachbon/smart-ralph · 45 tokens

ralph-specum-cancel

This skill should be used only when the user explicitly asks to use $ralph-specum-cancel, or explicitly asks Ralph Specum in Codex to stop execution or remove a spec.

tzachbon/smart-ralph · 45 tokens