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 ihatesea69/kiro-kit --skill deep-security-scangit clone --depth 1 https://github.com/ihatesea69/kiro-kitWrote 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/ihatesea69/kiro-kit/deep-security-scan)<a href="https://agentmods.dev/skills/ihatesea69/kiro-kit/deep-security-scan"><img src="https://agentmods.dev/badge/skills/ihatesea69/kiro-kit/deep-security-scan/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/ihatesea69/kiro-kit/deep-security-scan"><img src="https://agentmods.dev/badge/skills/ihatesea69/kiro-kit/deep-security-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.01275 |
| Opus 5.5 | $0.00020 | $0.00510 |
| Sonnet 5.5 | $0.00010 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
deep-security-scan 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 1mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Security Scan
Activate this skill when running a whole-repository deep security scan (the
/security:deep-scan command). It holds the methodology the security agents
share, the severity taxonomy, the hard exclusions that keep the false-positive
rate low, and the finding/report templates.
When to Use
- A user asks for a thorough, whole-repo security assessment (not a per-diff review).
- You are orchestrating or acting as one of the
security-recon,security-finder,security-triage,security-validator,security-judge, orsecurity-reporteragents.
When NOT to Use (scope boundary)
- Per-diff / pre-merge review → use
/review:security. That is the fast gate on changed lines; this scan is the slow, whole-repo sweep. - Infrastructure / compliance audit (IAM, container CVEs, CIS/SOC2) → use the
security-auditoragent. This scan owns application code vulnerabilities. - Avoid double-reporting: if a finding is purely an infra misconfiguration, defer it
to
security-auditor.
Methodology (three phases, per finder)
Adapted from published open-source security-review practice:
- Repository context — learn the frameworks, the existing sanitization/auth patterns, and the threat model BEFORE looking for bugs. (Recon produces this; finders consume it.)
- Comparative analysis — judge suspect code against the codebase's OWN secure patterns. Deviation from the house pattern is the strongest lead; absence of any pattern is judged against the framework's secure default.
- Vulnerability assessment — trace data flow from user-controlled inputs to sensitive sinks. A finding is a complete, reachable path with insufficient defense. Localize at suspicious-point (control-flow) granularity.
Pipeline shape
recon (1, serial) → finders (N, parallel) [+ semgrep → triage (N, parallel), optional]
→ validators (1 per candidate, parallel) → judge (1, serial dedup)
→ reporter (1, serial)
- Parallel finders each own a disjoint partition so they don't converge on the same obvious bug.
- Adversarial validators try to REFUTE each candidate and score confidence 1–10; everything < 8 is dropped.
- Serial judge dedups by ROOT CAUSE (new / better-example / duplicate) — serial so simultaneous duplicates aren't both accepted.
- Finders write results to files incrementally, so a dead subagent doesn't lose its partition's work.
What ships with it
7 files 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.
- 1mo ago First seen · 114 lines · 50 tokens per session scan A fb2c7a1df1e3
deep-security-scan is a skill published in the GitHub repository ihatesea69/kiro-kit (19 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,275 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 2026-09-03.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…