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 pedroiff0/awesome-skills --skill docker-compose-app-recoverygit clone --depth 1 https://github.com/pedroiff0/awesome-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/pedroiff0/awesome-skills/docker-compose-app-recovery)<a href="https://agentmods.dev/skills/pedroiff0/awesome-skills/docker-compose-app-recovery"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/docker-compose-app-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/pedroiff0/awesome-skills/docker-compose-app-recovery"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/docker-compose-app-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 | $0.00061 | $0.01370 |
| Opus 5 | $0.00030 | $0.00685 |
| Sonnet 5 | $0.00012 | $0.00274 |
| Haiku 4.5 | $0.00006 | $0.00137 |
Grade B, and why
docker-compose-app-recovery scanned grade B with 2 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 7d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- Live API: `curl -s -X POST http://localhost:<port>/api/auth/login -H 'Content-Type: application/json' -d '{"identifier":"<email>","password":"<pw>"}'` → `200` + JWT. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Live API: `curl -s -X POST http://localhost:<port>/api/auth/login -H 'Content-Type: application/json' -d '{"identifier":"<email>","password":"<pw>"}'` → `200` + JWT. How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docker-compose-app-recovery
Use this when a user is locked out of a docker-compose app, can't find a password, needs to reset an admin, or must read/write the app's database directly. The core insight: recover by writing to the DB from inside the app container, reusing the app's own dependencies (bcrypt + mongodb driver + connection string), then verify through the live API — not by grepping logs.
When this fires
- "Qual a senha de [email protected]?" and the password came from a seed.
- "Perdi a senha do admin / não consigo logar."
- "Preciso resetar a senha / criar um usuário admin."
- "Quero ler/alterar dados no banco do app no docker."
Steps
-
Locate the compose project.
find ~ -maxdepth 4 -iname 'docker-compose*.y*ml' cd <project>; docker compose psConfirm which service is the app (
app,web, ...) and the DB (mongo,postgres, ...). -
Map the auth model. Grep the source for how passwords are set:
grep -rniE "seed|admin|password|bcrypt" app/srcRead the seed file. Learn: (a) where the password is generated, (b) whether it is random and printed ONLY on first creation, (c) the hash lib + rounds (bcryptjs@12, argon2, etc.), (d) the user collection name and the discriminator field (
role,email,isAdmin). -
Recoverability check — usually UNRECOVERABLE. If the account already exists (
createdAtin the past) and the password was a one-time random seed printed only at first boot, it is gone:docker compose logs appwon't have it (it's only printed whencreatedis true).journalctl CONTAINER_NAME=...usually doesn't retain boot logs across recreations.- bcrypt/argon2 are one-way — the stored hash can't be reversed. Don't burn time grepping logs. Go straight to reset (step 4).
-
Reset by writing the DB from INSIDE the app container (not the host). The app container already has the exact bcrypt + mongodb driver and the same
MONGO_URI— reuse them so the hash is 100% compatible with the login path.- Write a temp script on the host (see
scripts/reset-password-in-container.js). - Run it via stdin, because the host file is NOT mounted at the container's
/appcwd:docker compose exec -T app node - < reset.js - The script: generate a strong password (
crypto.randomBytes(18).toString('base64url')), hash with the SAME lib+rounds the app uses, connect via the app'sMONGO_URI,updateOnethe user'spasswordHash, print the new password ONCE.
- Write a temp script on the host (see
What ships with it
2 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.
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.
- 7d ago First seen · 95 lines · 61 tokens per session scan B 9bf493962ff2
docker-compose-app-recovery is a skill published in the GitHub repository pedroiff0/awesome-skills (1 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 1,370 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hermes-mnemosyne
Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMESHOME/plugins/mnemosyne/.
hermes-self-evaluation
Use this skill when the user asks to audit, review, or optimize Hermes's own performance — analyzing session data, skills, configuration, costs, and usage patterns to identify improvements, automation opportunities, and system optimizations.
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.
svix-sending-webhooks
Everything for working with Svix webhooks: first-time setup (API key, SDK install, first message), Dispatch (sending webhooks to your customers), Ingest (receiving third-party webhooks), Applications, Channels, customer UIDs, idempotency, App Portal embedding, operational webhooks, the Svix CLI, and — only when the…
kubernetes-storage
Covers persistent data in the cluster — PersistentVolumes/Claims, StorageClasses and dynamic provisioning, access modes, StatefulSets, volume lifecycle, and reclaim policy so data survives rescheduling. Use this whenever the user is provisioning a PVC, choosing a StorageClass or access mode, running a stateful…
stateful-workloads
Covers running stateful systems — databases, queues, search indexes — on Kubernetes, including StatefulSets and stable identity, durable storage, backup and failover built into the platform rather than bolted on, and the tradeoff between self-managing a stateful service and paying for a managed one. Use this whenever…