ML-MLOps-Portfolio: Skill for Claude Code

.devin/skills/secret-breach-response/SKILL.md

secret-breach-response is a skill for Claude Code from DuqueOM/ML-MLOps-Portfolio. It costs 27 tokens per session (1,677 once invoked), scanned A, original, MIT.

An incident procedure for responding when passwords, access keys, tokens, or other secret credentials are exposed.

In plain words
What is it for?
It helps identify where and how a secret leaked, assess its urgency and scope, audit access, coordinate revocation and rotation with approval, notify people, and prepare a post-incident review.
Why use it?
It limits further damage by stopping related work, classifying the exposed credential, and preserving an audit trail before credentials are revoked or rotated.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is DuqueOM/ML-MLOps-Portfolio's own configuration. It tells Claude Code how to work on ML-MLOps-Portfolio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ML-MLOps-Portfolio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DuqueOM/ML-MLOps-Portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DuqueOM/ML-MLOps-Portfolio/main/.devin/skills/secret-breach-response/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DuqueOM/ML-MLOps-Portfolio

Made for: Claude Code.

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 secret-breach-response

README.md
[![agentmods](https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/secret-breach-response/github.svg)](https://agentmods.dev/skills/duqueom/ml-mlops-portfolio/secret-breach-response)
Your own site
<a href="https://agentmods.dev/skills/duqueom/ml-mlops-portfolio/secret-breach-response"><img src="https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/secret-breach-response/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 secret-breach-response

Your own site · 80×15
<a href="https://agentmods.dev/skills/duqueom/ml-mlops-portfolio/secret-breach-response"><img src="https://agentmods.dev/badge/skills/duqueom/ml-mlops-portfolio/secret-breach-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,677 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.
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 $0.00027 $0.01677
Opus 5 $0.00014 $0.00839
Sonnet 5 $0.00005 $0.00335
Haiku 4.5 $0.00003 $0.00168

Measured 12d ago against content hash 18842f34ca96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

secret-breach-response 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 12d 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.

.devin/skills/secret-breach-response/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Secret Breach Response

🚨 STOP EVERYTHING FIRST

If you are the agent:

  1. Halt any running pipeline step (CI deploy, K8s apply, image push)
  2. Emit:
    [AGENT MODE: STOP]
    Operation: Secret breach response
    Finding: <secret-type> exposed in <location>
    Waiting for: Human confirmation to proceed with rotation
    
  3. Do NOT attempt to rewrite git history or rotate credentials without explicit authorization. Silent rotation destroys the audit trail.

Phase 1 — Detect & Classify (AUTO)

Classify the exposed credential:

Type Example pattern Rotation urgency
AWS access key AKIA[0-9A-Z]{16} P1 — minutes
GCP service account JSON "private_key": "-----BEGIN PRIVATE KEY----- P1 — minutes
GitHub PAT ghp_[A-Za-z0-9]{36} P1 — minutes
Database password (variable) P2 — 1h
Internal API key (variable) P2 — 1h
Signing key (variable) P1 — minutes
Slack/webhook URL hooks.slack.com/services/... P3 — 24h

Determine exposure scope:

  • Where was the leak? (git log, CI logs, image layer, Slack message)
  • How long has it been exposed? (git commit timestamp, log retention)
  • Was it pushed to a public remote? (git log origin/main)
  • Did any external CI/CD run with the credential? (check workflow history)

Output classification to incidents/secret-breach-<YYYY-MM-DD-HHMM>.md.

Phase 2 — Revoke Credential (STOP before proceeding)

This phase requires human confirmation. Agent proposes, human executes.

AWS

# Delete the access key at the root of the tree
aws iam delete-access-key --access-key-id <AKIA...> --user-name <username>
# OR disable it first if investigation needed:
aws iam update-access-key --access-key-id <AKIA...> --status Inactive --user-name <username>

GCP

# Delete the service account key
gcloud iam service-accounts keys delete <KEY_ID> \
  --iam-account=<service-account-email>

Read the full file on GitHub · 195 lines

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. 12d ago First seen · 195 lines · 27 tokens per session scan A 18842f34ca96

Subscribe to this mod's changes

secret-breach-response is a skill published in the GitHub repository DuqueOM/ML-MLOps-Portfolio (5 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 1,677 once invoked, about $0.0001 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.