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 skills/n-n-code/n-n-code-skills/securitynpx skills add n-n-code/n-n-code-skills --skill securitygit clone --depth 1 https://github.com/n-n-code/n-n-code-skillsWrote 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/n-n-code/n-n-code-skills/security)<a href="https://agentmods.dev/skills/n-n-code/n-n-code-skills/security"><img src="https://agentmods.dev/badge/skills/n-n-code/n-n-code-skills/security.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.01957 |
| Opus 5 | $0.00036 | $0.00979 |
| Sonnet 5 | $0.00014 | $0.00391 |
| Haiku 4.5 | $0.00007 | $0.00196 |
Grade A, and why
security 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 3d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security
Find and reduce realistic abuse paths while keeping evidence, authority, and side effects explicit.
Compose with security-identity-access when identity or tenant-authorization
boundaries are central. That companion owns identity-specific checks; this
skill owns the shared investigation, safety, evidence, and reporting contract.
Choose The Mode And Authority
| Mode | Use when | Authority |
|---|---|---|
security review |
Determine whether concrete code, configuration, or a change creates security-relevant weaknesses or unsafe exposures | Read-only: do not edit source or configuration or change external state |
threat model |
Map assets, boundaries, attacker goals, abuse paths, and mitigations | Read-only: do not edit the system or present scenarios as confirmed vulnerabilities |
secure implementation |
Design, implement, or remediate security-sensitive behavior | Mutate only the files or systems explicitly authorized by the request |
Writing an explicitly requested report does not authorize remediation. If a request combines analysis and implementation, keep the initial investigation read-only and make the transition to changes visible.
Shared Workflow
- Set scope and assumptions. Identify the mode, target paths and environments, protected assets, plausible attacker capabilities, deployment shape, and relevant authorization assumptions. Inspect discoverable context before asking questions; ask only when an answer would materially change scope, authority, or ranking.
- Map the system. Trace entrypoints, data flows, trust boundaries, authoritative controls, storage, external integrations, and observable effects. Follow a path across all participating components rather than stopping at a frontend, handler, or risky-looking call.
- Choose high-value hypotheses. Derive a small set of abuse paths from the actual architecture and attacker goals. Prioritize paths involving authority, isolation, code or query execution, external resource access, dangerous parsing, sensitive data, or resource exhaustion when those surfaces exist.
- Trace each hypothesis. Establish input provenance, transformations, guards, reachability, attacker prerequisites, sink behavior, and concrete impact. Check middleware order, authorization placement, schemas, parameterization, encoding, and configuration already in effect. A risky API, scanner alert, or pattern match is a lead, not a finding.
- Verify material protections. When a conclusion depends on a framework, runtime, or library default, identify the resolved dependency and effective configuration, then verify the behavior using matching authoritative documentation, source, or a minimal safe reproduction. If that evidence is unavailable, classify the path as needing validation rather than assuming either safety or vulnerability.
- Classify, act, and report. Use the evidence outcomes below, stay within the selected mode, and produce its required output.
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.
- 3d ago First seen · 195 lines · 72 tokens per session scan A 2fd27950e4d2
security is a skill published in the GitHub repository n-n-code/n-n-code-skills (4 stars, last pushed 5d ago), licensed MIT. It adds 72 tokens to every session and 1,957 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 2026-08-31.
Other skills, from other repositories
cocowatch
Developer engagement observer — non-blocking, always-on observational layer that tracks Delegation Intensity, Review Depth, and Engagement Zone throughout a session. Summary surfaced at $ship and FULL checkpoints.
the-grilling
Use when adversarial brainstorming is needed after reconnaissance — the Proposer, Devils-Advocate, and Synthesizer each run ONE pass (no rounds); the Don is grilled on the IDEA first, one question at a time, then the proposal is attacked.
using-gangsta
Use when starting any conversation — establishes how to find and use Gangsta skills, enforces the 1% invocation rule, maps platform tools, and routes the Don's intent through the Gangsta Agents Family hierarchy.
interrogation-debugging
Use when encountering any bug, test failure, or unexpected behavior — finds the rat in the code through systematic root-cause interrogation before any fix attempts.
exit-strategy
Use when implementation is complete and all tests pass — guides the clean exit from a development branch with structured options for merge, PR, or cleanup.
omerta
Use when enforcing governance guardrails during any gangsta operation — referenced as cross-cutting concern by all skills for anti-hallucination, authorization, state durability, resource management, and spec supremacy rules.