environment-contract-audit

environment-contract-audit is a skill for Codex from OutlineDriven/outline-driven-development. It costs 37 tokens per session (665 once invoked), scanned A, original, Apache-2.0.

A read-only check that compares environment variables used by code and deployment files with the places that supply them. Environment variables are configuration values provided outside the program, such as service URLs or secrets.

In plain words
What is it for?
Use it to audit environment files, runtime settings, CI secrets, templates, and deployment configuration.
Why use it?
It finds missing, undocumented, incorrectly scoped, or unsafe configuration before the application runs or deploys.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to audit environment files, runtime settings, CI secrets, templates, and deployment configuration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/outline-driven-development/environment-contract-audit
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.

Any agent
npx skills add OutlineDriven/outline-driven-development --skill environment-contract-audit
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-development

Made for: Codex.

Wrote 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.

agentmods badge for environment-contract-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/environment-contract-audit/github.svg)](https://agentmods.dev/skills/outlinedriven/outline-driven-development/environment-contract-audit)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/environment-contract-audit"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/environment-contract-audit/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.

agentmods 80×15 button for environment-contract-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/environment-contract-audit"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/environment-contract-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00037 $0.00665
Opus 5 $0.00018 $0.00332
Sonnet 5 $0.00007 $0.00133
Haiku 4.5 $0.00004 $0.00067

Measured 5d ago against content hash 4458350db449, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

environment-contract-audit 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.devin/skills/environment-contract-audit/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Environment contract audit

Contract

Field Bound contract
Trigger Environment-dependent code, templates, or deployment configuration changes, or runtime configuration is missing.
Authority Read-only local inspection. Approval required only for production secret, credential, or remote configuration mutation: make one harness ask/question call before the run starts; 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.

Inputs

  • Declared surfaces (required): the code, templates, runtime config files, and deployment config to audit. Named by the user or inferred from the change diff.
  • Supply sources (required): env files, CI secret definitions, deployment manifests, and any other location that provides variable values.

Procedure

  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.

Read the full file on GitHub · 38 lines

Files

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.

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. 5d ago First seen · 38 lines · 37 tokens per session scan A 4458350db449

Subscribe to this mod's changes

environment-contract-audit is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 665 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.