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 agentmods add instructions/n-shadloo/secure-code-auditor/gemini-mdgit clone --depth 1 https://github.com/n-shadloo/secure-code-auditorWhat 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 | $0.00467 | $0.00467 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
secure-code-auditor GEMINI.md 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 2d 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.
What it actually says
Gemini CLI context: secure-code-auditor
This repository's security instructions live in SKILL.md and references/.
Load SKILL.md first. Then open only the references/*.md file(s) for the
concern in front of you. Do not duplicate the content here — read the source
files.
The router in SKILL.md is grouped: the OWASP Top 10:2025 spine, then
cross-cutting surfaces, then package decisions. Pick the group, then the row.
Where two rows could both match, the "Ownership and boundaries" table below
the router names the one file that owns the topic.
At review-time, read references/01-audit-workflow.md before any topic file.
It owns the sweep: the phase order, the entry-point inventory, principals and
boundaries, source-to-sink pairing, the six-item verification gate, and the
coverage ledger. The topic files answer the questions the sweep generates,
rather than the ones the codebase made obvious. The codebase stays read-only,
and the report ends with what was not reviewed.
At write-time, apply the secure defaults from the reference the router names. Where a default conflicts with the request, apply the default and say so in one line. Close with a short security-decisions note rather than a findings report.
references/00-methodology-and-severity.md holds mode selection and both
output formats. It also holds the severity rubric with its baseline table,
the finding schema, the ASVS 5.0 chapter mapping, and the conflict rule.
Three read-only triage scripts sit under scripts/. They are standard
library only, they make no network calls, and they never import the audited
project. --json is JSON Lines in all three, and every stream ends with one
kind: "summary" record. Every row names the reference file that owns it.
Treat their output as leads to verify, not as confirmed findings.
The primary integration is Claude. This file exists so that Gemini CLI uses
the same single source of truth. See AGENTS.md for the fuller description.
The version is recorded in the SKILL.md frontmatter (metadata.version).
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.
- 2d ago First seen · 38 lines · 467 tokens per session scan A 7b3ec5db949b
secure-code-auditor GEMINI.md is an instructions file published in the GitHub repository n-shadloo/secure-code-auditor (4 stars, last pushed 5d ago), licensed MIT. It adds 467 tokens to every session, about $0.0023 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.
Other instructions, from other repositories
skills AGENTS.md
Instructions for qdrant/skills, covering qdrant skills, project overview, project structure, navigating skills locally and conventions.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
nezha AGENTS.md
AGENTS.md instructions for hanshuaikang/nezha, covering nezha — agents.md, 项目概述, 开发命令, 架构设计 and 前端（src/）.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
toki AGENTS.md
Instructions for choi138/toki, covering workspace rules, source of truth, toki workflow, required checks and global safety rules.