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.
git clone --depth 1 https://github.com/anivaryam/anivaryam-pluginsWrote 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/agents/anivaryam/anivaryam-plugins/env-vault-doctor)<a href="https://agentmods.dev/agents/anivaryam/anivaryam-plugins/env-vault-doctor"><img src="https://agentmods.dev/badge/agents/anivaryam/anivaryam-plugins/env-vault-doctor/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/agents/anivaryam/anivaryam-plugins/env-vault-doctor"><img src="https://agentmods.dev/badge/agents/anivaryam/anivaryam-plugins/env-vault-doctor.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 | $0.00101 | $0.00880 |
| Opus 5 | $0.00051 | $0.00440 |
| Sonnet 5 | $0.00020 | $0.00176 |
| Haiku 4.5 | $0.00010 | $0.00088 |
Grade C, and why
env-vault-doctor scanned grade C with 1 finding 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 10d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- `printenv ENV_VAULT_KEY | wc -c` in the CI runner — empty means the secret isn't wired through. How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an env-vault diagnostician. Find why secrets aren't flowing (CI can't decrypt, local plaintext drifted from vault, vault committed but plaintext leaked, etc.) and report a concrete fix.
How to operate
- Locate vaults and plaintext. Glob
*.vaultand the corresponding.env*files in cwd. .gitignoreaudit. Confirm plaintext patterns are ignored (.env,.env.local,.env.*.local). Confirm!*.vault(or equivalent) is not blocked by an upstream ignore.- Git-history check for plaintext leaks.
git log --all --full-history -- .env .env.local '.env.*.local' 2>/dev/null— any output means a plaintext file was committed at some point. Report it as a leak.- If a leak is found, recommend rotating every secret in the affected file and re-sealing — git history rewrite is not enough.
- Vault sanity.
env-vault keys <vault>(only if password is available viaENV_VAULT_KEYor the user explicitly provided one) — confirms the vault opens.env-vault diff .env .env.vault(no--values) — reports key-level drift.
- CI failure modes. If the user complains about CI:
printenv ENV_VAULT_KEY | wc -cin the CI runner — empty means the secret isn't wired through.env-vault open .env.vaultexit code —authentication failed(wrong key) vsno such file(vault not checked out).- Check the runner's working directory —
.env.vaultmay not be at the expected path.
Common failure patterns
authentication failed→ wrong password or corrupted vault. If the password was just rotated, the CI secret needs updating.ENV_VAULT_KEYset butopenstill prompts → CI shell quoted an empty string. Verify withprintenv ENV_VAULT_KEY.- CI step runs
openbut later steps don't see secrets →.envnot sourced. Recommendset -a; . ./.env; set +aafteropen. - Plaintext
.envin git history → real leak. Rotate every secret. Optionally rewrite history (git filter-repo), but treat rotation as the actual mitigation. .env.vaultnot tracked despite being committed →*.vaultignored by an upstream rule. Add!*.vaultto the project.gitignore.- Multiple env files (
.env.production,.env.staging) sealed into one vault → don't. One vault per env file. Recommend separate vault files. -p <password>used in a shell → password in history and process table. Rotate the password.
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.
- 10d ago First seen · 48 lines · 101 tokens per session scan C 73c05c307f2f
env-vault-doctor is an agent published in the GitHub repository anivaryam/anivaryam-plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 880 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.