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 commands/sifxprime/kodelyth-ecc/security-auditgit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote 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/commands/sifxprime/kodelyth-ecc/security-audit)<a href="https://agentmods.dev/commands/sifxprime/kodelyth-ecc/security-audit"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-ecc/security-audit.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 | $0.00025 | $0.00465 |
| Opus 5 | $0.00013 | $0.00233 |
| Sonnet 5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
security-audit 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 yesterday.
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
/security-audit — Parallel Security Audit
Three security-focused agents fire simultaneously. What would take an hour one-by-one finishes in 15 minutes.
What Gets Launched in Parallel
| Agent | Focus |
|---|---|
security-reviewer |
OWASP Top 10, secrets in code, injection, XSS, CSRF, auth gaps, crypto misuse |
dependency-doctor |
CVEs in deps, outdated packages, transitive vulnerabilities, license issues |
api-guardian |
Exposed endpoints, missing auth, broken contracts, data leakage in responses |
Usage
/security-audit # full repo
/security-audit src/auth/ # focus on auth module
/security-audit --pre-deploy # adds environment + secrets check
Report Format
## SECURITY AUDIT REPORT
### Vulnerabilities (security-reviewer)
CRITICAL: [list]
HIGH: [list]
MEDIUM: [list]
### Dependencies (dependency-doctor)
CVE: [list with severity]
OUTDATED: [list]
### API Surface (api-guardian)
EXPOSED: [list]
WARN: [list]
---
TOTAL: X critical, Y high, Z medium
ACTION: [ship / patch first / block]
When to Use
- Before any production deploy
- After adding new auth or payment flows
- When a dep audit flags CVEs
- Quarterly security health check
Execute Now
Invoking this command is confirmation to proceed. Execute immediately:
- Determine scope from
$ARGUMENTS. Default: entire current project. - Spawn all agents simultaneously with
run_in_background: true:security-reviewer— full OWASP scan of codebasedependency-doctor— CVE audit of all package manifestsapi-guardian— API surface exposure check
- Wait for all to complete.
- Aggregate into the Security Audit Report format above.
- End with: "Which vulnerability do you want to fix first?"
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.
- yesterday First seen · 67 lines · 25 tokens per session scan A 76d091fa5d2d
security-audit is a command published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 465 once invoked, about $0.0001 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 commands, from other repositories
csm-beliefs
Review belief knowledge, run a belief scan, and preview promotions.
csm-governance
Run memory governance — dedup detection, candidate and archive reports, merges.
csm-recall
Search project memory and assemble focused evidence for the current task.
csm-brief
Build a context brief for the current task from prior sessions.
csm-checkpoint
Create or inspect durable checkpoints of expensive-to-reconstruct state.
csm-compaction
Show context pressure and audit compaction behavior.