security

A repository security check that looks for leaked secrets, risky code patterns, and vulnerable packages, then shows where incoming data reaches a finding.

In plain words
What is it for?
Run a deep scan, investigate findings, trace inputs through the code, and identify when a scanner did not run.
Why use it?
It prevents known credentials and serious security problems from being overlooked. Blocking findings must be fixed and checked again.

Command

Install

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.

agentmods
npx agentmods add commands/azrtydxb/procoder/security
Clone the repo
git clone --depth 1 https://github.com/azrtydxb/procoder
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00367
Opus 5 $0.00013 $0.00183
Sonnet 5 $0.00005 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 2d ago against content hash e4d5b40fb8a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.kilo/commands/security.md · 31 lines

What it actually says

The user invoked /procoder:security with arguments: $ARGUMENTS

The command below is the procoder binary on PATH.

First read .procoder/security/RULES.md and follow it — the repo's rules win. If it is missing, get the default via procoder templates, write it, then continue.

  1. Run procoder security --deep. Three instruments answer:
    • secrets (gitleaks) — every finding BLOCKS; remove the secret AND tell the user to rotate the credential (removal alone is not enough — assume it leaked the moment it was written).
    • SAST (semgrep, community rules) — ERROR severity blocks; judge WARNING/INFO honestly: fix what is real, explain what is not.
    • dependency vulns (osv-scanner) — high/critical blocks; upgrade the package or explain why not.
  2. Rank what you review first with the index: procoder index entrypoints is where data enters; procoder index callers <symbol> traces how input reaches a finding (procoder index graph for the full walk).
  3. NOT-checked lines mean a scanner is missing — run procoder init. A security check that silently didn't run is worse than a red one.
  4. Fix, then re-run procoder security --deep until no blocking findings remain, and show the user the final report with your judgments.

Never print a secret's value — name the rule, the file, the line, and the rotation duty.

Changes

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.

  1. 2d ago First seen · 31 lines · 25 tokens per session scan A e4d5b40fb8a4

Subscribe to this mod's changes

security is a command published in the GitHub repository azrtydxb/procoder (196 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 367 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 2026-08-30.