secret-detection

secret-detection is a skill for Claude Code, Codex from IBM/mcp-context-forge. It costs 54 tokens per session (372 once invoked), scanned A, original, Apache-2.0.

A workflow for handling findings from detect-secrets, a tool that scans code and documents for values that look like credentials. It covers both real secrets and reviewed false positives.

In plain words
What is it for?
Use it when a secret scan fails, when adding credential-like placeholders to documentation or code, or when resolving changes to the secrets baseline.
Why use it?
It helps remove exposed credentials and prevents approved examples from repeatedly failing scans. It also gives specific ways to resolve conflicts in the scan baseline.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it when a secret scan fails, when adding credential-like placeholders to documentation or code, or when resolving changes to the secrets baseline.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ibm/mcp-context-forge/secret-detection
About the project

ContextForge is an open-source gateway and registry that brings MCP, A2A, REST, and gRPC tools, agents, and APIs together behind one endpoint. It helps teams discover, govern, observe, authenticate, and route calls across AI infrastructure. The catalogue add-ons support operating and extending this gateway.

IBM/mcp-context-forge · 4,832 stars · on GitHub · ibm.github.io

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 IBM/mcp-context-forge --skill secret-detection
Clone the repo
git clone --depth 1 https://github.com/IBM/mcp-context-forge

Made for: Claude Code, 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 secret-detection

README.md
[![agentmods](https://agentmods.dev/badge/skills/ibm/mcp-context-forge/secret-detection/github.svg)](https://agentmods.dev/skills/ibm/mcp-context-forge/secret-detection)
Your own site
<a href="https://agentmods.dev/skills/ibm/mcp-context-forge/secret-detection"><img src="https://agentmods.dev/badge/skills/ibm/mcp-context-forge/secret-detection/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-detection

Your own site · 80×15
<a href="https://agentmods.dev/skills/ibm/mcp-context-forge/secret-detection"><img src="https://agentmods.dev/badge/skills/ibm/mcp-context-forge/secret-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 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 $0.00054 $0.00372
Opus 5.5 $0.00022 $0.00149
Sonnet 5.5 $0.00011 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured today against content hash cee11e04539d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

secret-detection 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.

.agents/skills/secret-detection/SKILL.md · 22 lines

What it actually says

Secret Detection (detect-secrets)

Prefer removing the trigger. Rewrite the line so it holds no credential-shaped value. Suppress only when the value must stay.

Suppress a False Positive

  • Python files: suppress inline with # pragma: allowlist secret. The finding then stays out of .secrets.baseline after make detect-secrets-scan.
    • Exception: doctest strings where the comment breaks the assertion. Rely on .secrets.baseline and audit with make detect-secrets-audit.
  • Makefile: suppress audited false positives inline with # pragma: allowlist secret. In variable assignments, append the pragma directly after the value, with no space. Make keeps whitespace before a comment in the value.
  • Markdown: inside a fenced code block, append # pragma: allowlist secret to the line. In prose, append <!-- pragma: allowlist secret -->. Rewrite the line instead when the pragma would break a sample that readers copy verbatim.
  • All other file types: regenerate the baseline with make detect-secrets-scan.
  • Merge conflicts: resolve .secrets.baseline with the version from main.

Verify

Run make detect-secrets-scan. It exits non-zero on live or unaudited findings. Remediate with make detect-secrets-audit. Done when the command exits zero and .secrets.baseline holds no entry for a line you suppressed or removed.

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. today First seen · 22 lines · 54 tokens per session scan A cee11e04539d

Subscribe to this mod's changes

secret-detection is a skill published in the GitHub repository IBM/mcp-context-forge (4,832 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 372 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-17.

Related

secret-detection compared with skills from other repositories

secret-detection next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
secret-detectionIBM/mcp-context-forgeSkill4.8ktodayApache-2.0A54Claude Code, Codex
cis-aws-foundations-4.10CyberStrikeus/CyberStrikeSkill3.6ktodayAGPL-3.0A22Claude Code, Codex
rowboat-spacesrowboatlabs/rowboatSkill18kyesterdayApache-2.0A60Claude Code, Codex
create-tech-designhumanlayer/humanlayerSkill13kyesterdayApache-2.0A16Claude Code, Codex
deploy-docker-composeomnigent-ai/omnigentSkill11ktodayApache-2.0A84Claude Code, Codex
haikuagno-agi/agnoSkill43ktodayApache-2.0A0Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2ktodayMITA78Claude Code