agent-environment-retr…
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.
Use when environment-dependent code, templates, or deployment configuration changes, or when runtime configuration is missing. Produces a bidirectionally reconciled environment-variable contract.
$ npx -y skills add OutlineDriven/odin-claude-plugin --skill environment-contract-audit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/environment-contract-auditContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when environment-dependent code, templates, or deployment configuration changes, or when runtime configuration is missing. Produces a bidirectionally reconciled environment-variable contract.
name: environment-contract-audit description: 'Use when environment-dependent code, templates, or deployment configuration changes, or when runtime configuration is missing. Produces a bidirectionally reconciled environment-variable contract.'
| Field | Bound contract | |---|---| | Trigger | Environment-dependent code, templates, or deployment configuration changes, or runtime configuration is missing. | | Authority | Human-gated: makes one harness ask/question call before any production secret, credential, or remote configuration mutation; otherwise read-only. No file, VCS, credential, paid, published, deployed, or remote mutation without that approval. Prose consent, invocation consent, prior-run consent, and post-start discovery do not approve an effect. | | Side effect | Bidirectionally reconciled environment-variable contract. | | Done | Every referenced variable is supplied and documented at the correct required/optional and public/secret scope. | | Stop | exact blocker; unsafe exposure. Bound: declared code, templates, runtime config, and deployment-config surfaces. |
1. Enumerate every environment variable referenced across the declared surfaces. Split each into required vs optional and public vs secret. **Done when:** the full variable inventory is compiled with scope annotations. 2. For each variable, check the supply side (env files, CI secrets, deployment config) and the consumption side (code reads, template interpolations). Bidirectionally reconcile: flag variables consumed but not supplied, supplied but not consumed, and scope mismatches (a secret consumed where a public value is expected, or vice versa). **Done when:** every variable has a supply-side and consumption-side status recorded. 3. For each mismatch, determine the correct resolution: add the missing supply, remove the dead reference, correct the scope, or document the intentional override. Do not mutate production secrets, credentials, or remote config without the start approval. **Done when:** every mismatch has a named resolution. 4. Produce the reconciled contract: a table listing each variable with its name, required/optional scope, public/secret scope, supply source, consumption sites, and resolution status. **Done when:** the contract table is complete and every variable is accounted for.
A bidirectionally reconciled environment-variable contract: a table of every referenced variable with required/optional scope, public/secret scope, supply source, consumption sites, and resolution status. Terminal classification: `reconciled` (every variable supplied and documented at correct scope), `partial` (some mismatches remain with named resolutions), `blocked` (an exact blocker prevents reconciliation), or `unsafe-exposure` (a secret would be exposed; stopped before mutation).
Formerly the ODIN Claude Plugin. The repository URL is unchanged. Outline-Driven Development, nicknamed ODIN, is a highly opinionated code-agent skill library: principles-first engineering, surgical editing, and workflow automation, published as installable
Repo: OutlineDriven/odin-claude-plugin
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.
Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential,…
Use when a human explicitly asks for a full repository agent-compatibility pass returning a scored report with prioritized fixes. Not for tasks that require…
Use when setting up a project, auditing agent command permissions, or asking which read-only bash commands and domains to allow. Not for remote, credential,…
Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or…
Use when the user asks to make the skills framework work in a new harness, IDE, or CLI. Not for remote, credential, publish, deploy, or irreversible changes.