Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasnpx agentmods add skills/tahirraufkeeyu/software-development-agent-stack--sdas/secret-scannerWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/secret-scanner)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/secret-scanner"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/secret-scanner/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/tahirraufkeeyu/software-development-agent-stack--sdas/secret-scanner"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/secret-scanner.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 | $0.00075 | $0.01677 |
| Opus 5 | $0.00037 | $0.00839 |
| Sonnet 5 | $0.00015 | $0.00335 |
| Haiku 4.5 | $0.00007 | $0.00168 |
Grade A, and why
secret-scanner 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger this skill on any of:
- "Scan this repo for secrets / leaked keys / API tokens."
- "We think a credential was committed — help us remediate."
- "Repo is going public next week."
- Pre-merge hook that needs to refuse commits with new secrets.
Do not use this skill for live runtime secret detection (key rotation monitoring, cloud config scanning). Use it for code-at-rest and git history only.
Inputs
REPO_PATH(default:.) — path to the git repo.ALLOWLIST(default:.gitleaks.tomlor.secret-scanner-allowlist.yamlat repo root) — known false positives.OUT_DIR(default:./secret-scan-out).SCAN_REFLOG(default:1) — also scan reflog + stash refs.- Optional env:
TRUFFLEHOG_CONFIG— path to a custom trufflehog config.REDACT(default:1) — redact matched values in reports.
Outputs
gitleaks-report.json— raw Gitleaks findings.trufflehog-report.json— raw TruffleHog findings.secrets.deduped.json— unified, allowlist-filtered, deduplicated result.secrets-report.md— human report with per-finding remediation steps.
Each unified record:
{
"id": "sha256(commit|file|rule|match)[0:12]",
"rule": "aws-access-key",
"file": "src/infra/deploy.sh",
"commit": "a1b2c3d",
"author": "[email protected]",
"date": "2024-06-12T09:14:22Z",
"line": 42,
"redacted_match": "AKIA****************",
"verified": true,
"severity": "critical",
"allowlisted": false
}
Tool dependencies
git>= 2.30.gitleaks>= 8.18 (https://github.com/gitleaks/gitleaks).trufflehog>= 3.63 (https://github.com/trufflesecurity/trufflehog).jqfor merging.- Optional:
git-filter-repo(preferred over BFG) for rewriting history.
Procedure
- Confirm
$REPO_PATHis a git repo (git rev-parse --is-inside-work-tree). - Fetch all refs first:
git fetch --all --tags --prune. - Run
scripts/nuclear-scan.sh "$REPO_PATH" "$OUT_DIR"which executes Gitleaks (detect + protect), TruffleHog over the git file URI, and iterates branches, tags, reflog, and stash refs. - Merge the two JSON outputs. Key by
(commit_sha, file_path, rule_id, match_sha256)and dedupe. - Apply allowlist: drop records whose
(file_path, rule_id)pair matches a regex in the allowlist. Every drop keeps askipped_by_allowlistcounter that is logged. - Triage: for every remaining record,
- Verify with TruffleHog's
--only-verifiedstyle detector when possible (setsverified: true|false). - Classify severity: verified live credential -> Critical; historical credential known rotated -> High; placeholder or test -> Low.
- Verify with TruffleHog's
- Emit
secrets-report.mdcontaining:- Top-line counts by severity.
- A "Remediation sequence" section (always this order):
- Rotate the credential at the issuer (AWS, GitHub, Stripe, ...). Never do history rewrite first — a rewritten commit doesn't revoke a live key.
- Invalidate any cached credential (CI secret store, deploy platform env vars, developer laptops).
- Rewrite history with
git filter-repo(preferred) or BFG. - Force-push (coordinate with team). Every collaborator re-clones.
- Update the allowlist with a post-rotation hash so the dead secret doesn't re-trigger alerts.
- Provide exact commands tailored to each finding:
git filter-repo --invert-paths --path <file>when the file should go.git filter-repo --replace-text replacements.txtwhen only the secret should be scrubbed, preserving surrounding content.
- Return non-zero if any verified Critical remains.
What ships with it
1 file 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 · 160 lines · 75 tokens per session scan A 8779d8ccf0c0
secret-scanner is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 1,677 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.