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 skills add vivekkrishna/agentic-validation-skills --skill cige-environment-recoverygit clone --depth 1 https://github.com/vivekkrishna/agentic-validation-skillsWrote 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.
[](https://agentmods.dev/skills/vivekkrishna/agentic-validation-skills/cige-environment-recovery)<a href="https://agentmods.dev/skills/vivekkrishna/agentic-validation-skills/cige-environment-recovery"><img src="https://agentmods.dev/badge/skills/vivekkrishna/agentic-validation-skills/cige-environment-recovery/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.
<a href="https://agentmods.dev/skills/vivekkrishna/agentic-validation-skills/cige-environment-recovery"><img src="https://agentmods.dev/badge/skills/vivekkrishna/agentic-validation-skills/cige-environment-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.00476 |
| Opus 5 | $0.00024 | $0.00238 |
| Sonnet 5 | $0.00010 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
cige-environment-recovery 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 today.
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.
What it actually says
CIGE: EnvironmentRecoveryAgent
Invoked by cige-failure-classification when a run is classified as an Infrastructure Failure. Restores the environment; never touches the test definition.
When to invoke
- Execution failed before reaching the system under test: auth error, service unreachable, missing seed data, ephemeral environment not bootstrapped
- You have already confirmed (via
cige-failure-classification) that this is an environment problem, not a product defect or stale test
If you are not confident the failure is infrastructure-only, do not use this skill — go back to cige-failure-classification.
What it does
- Reads
Contextto identify what needs restoring: environment type, preconditions (seed data, auth state, feature flags), dependent services. - Attempts recovery:
- Re-authenticate
- Re-seed data
- Restart or reconnect dependencies
- Re-provision the ephemeral environment if it wasn't bootstrapped
- Re-runs the test in full after recovery.
- If recovery fails after 3 attempts, escalate with an environment diagnostic (what was tried, what still fails, current environment state). Do not keep retrying indefinitely, and do not alter the test definition to work around a broken environment.
Field permissions
| Field | Permission |
|---|---|
Context |
Read-only — used to know what to restore, never rewritten |
Intent |
Never touch |
Guardrails |
Never touch |
Execution[] |
Never touch |
The test is not the problem, so nothing about the test changes. The only output of this skill is either a restored environment (silent success, test re-run) or an escalation.
Human gate
Not required for recovery attempts themselves — environment restoration (re-auth, re-seed, restart) is reversible and routine. Required only when escalating a persistent failure after 3 attempts; the escalation should go to a human, not trigger a test-definition change on its own.
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.
- today Changed · +5 lines · +48 tokens per session b846bf179746
- 11d ago First seen · 39 lines · 0 tokens per session scan A 354877b7b7ac
cige-environment-recovery is a skill published in the GitHub repository vivekkrishna/agentic-validation-skills (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 476 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 2026-08-31.
Other skills, from other repositories
phx-work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after phx-plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
lab:autoresearch
Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.
codex-loop
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.