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 ShulkwiSEC/bb-huge --skill aikido-triagegit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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/shulkwisec/bb-huge/aikido-triage)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/aikido-triage"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/aikido-triage/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/shulkwisec/bb-huge/aikido-triage"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/aikido-triage.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 | $0.00000 | $0.03057 |
| Opus 5 | $0.00000 | $0.01528 |
| Sonnet 5 | $0.00000 | $0.00611 |
| Haiku 4.5 | $0.00000 | $0.00306 |
Grade A, and why
aikido-triage 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aikido Findings Triage Workflow
You are triaging an Aikido SAST/SCA/secret-scanning CSV export against a local codebase. Your job is to read every finding, investigate the flagged code, and verdict each one with evidence. At the end you produce a reviewed CSV and a self-contained HTML report.
Do not guess. Read the actual files before rendering a verdict.
Arguments
Parse from the user's invocation:
CSV_PATH— path to the Aikido CSV exportCODEBASE_PATH— absolute path to the local codebase to investigate
If either argument is missing, ask the user before proceeding.
Phase 1 — Parse the CSV
-
Read
CSV_PATHwith the Read tool. -
Parse every row. Key columns to extract per finding:
aikido_issue_id— unique IDtype—sast|open_source|leaked_secret|eolseverity— critical / high / medium / lowaffected_file— relative path to the flagged filerelated_cve— CVE or advisory ID (may be empty)rule— rule name that firedstart_line/end_line— flagged line rangeinstalled_version/patched_version— for SCA findingsaffected_package— for SCA/EOL findings
-
Group findings by
typeso you can batch-investigate efficiently.
Phase 2 — Investigate Each Finding
Work through findings type by type. For each one, read the flagged file and apply the investigation playbook for that type.
2a — leaked_secret findings
Step 1 — Does the file exist?
Use the Read tool on CODEBASE_PATH/affected_file. If the file does not exist:
→ Verdict: CLOSE — File Removed
→ Note: "File does not exist at HEAD. Finding references removed code in git history."
→ Move on. Do not investigate further.
Step 2 — Read the flagged lines.
Read start_line to end_line (expand by ±3 lines for context).
Apply these patterns:
| What you see | Verdict |
|---|---|
ENV.fetch(...), ENV[...], ENV.fetch(..., nil) |
CLOSE — False Positive (env var read) |
${{ secrets.* }} (GitHub Actions) |
CLOSE — False Positive (GH Actions secret) |
${VARIABLE_NAME} in .npmrc/.env.example |
CLOSE — False Positive (env var placeholder) |
--mount=type=secret in Dockerfile |
CLOSE — False Positive (Docker build secret) |
| A long regex, UA string, or binary-looking data | CLOSE — False Positive (pattern mismatch) |
| An actual hardcoded token/key/password string | KEEP OPEN — check liveness if possible |
| A real URL with embedded credentials (user:pass@host) | KEEP OPEN |
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.
- 12d ago First seen · 303 lines · 0 tokens per session scan A 7f18e1552a2e
aikido-triage is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,057 tokens. 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 2026-08-30.
Other skills, from other repositories
skill-coverage-audit
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs.
Code Review
Review a diff or PR for concrete behavioral defects and Home23 invariants.
source-coding-discipline
Use when a task involves reading, editing, reviewing, testing, debugging, refactoring, or otherwise working with source code files. Source paths include /.{py,ts,tsx,js,jsx,mjs,go,rs,java,kt,swift,rb,c,cc,cpp,h,hpp,sh,bash,zsh,sql,vue,svelte}. Do not use for docs-only, planning-only, or non-code file tasks unless the…
code-reviewer
Automated code review using official Claude Code plugin with parallel agents. Integrates ralph-security for OWASP validation and ralph-frontend for accessibility checks. Uses LSP for efficient code navigation.
sec-context-depth
Comprehensive AI code security review using 27 sec-context anti-patterns. Use for code review when security vulnerabilities are suspected, especially for AI-generated code.
adversarial
Apply adversarial opposite-analysis to plans, specs, architecture, code changes, and claims. Use when the user asks for adversarial review, opposing analysis, contrarian review, or red-team reasoning.