check

A command that scans a software project for common rule violations and produces a compliance report. It checks source files, repository status, task state, and repeated errors in the error log.

In plain words
What is it for?
Finding missing type hints, unsafe exception handling, debug output, hardcoded secrets, unfinished markers, meaningless assertions, oversized files, and uncommitted changes.
Why use it?
It gathers many code-quality and process checks in one report, making issues easier to find before they cause failures or review problems.

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/tk-logl/sentinel/check
Clone the repo
git clone --depth 1 https://github.com/tk-logl/sentinel
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 497 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 $0.00012 $0.00497
Opus 5 $0.00006 $0.00249
Sonnet 5 $0.00002 $0.00099
Haiku 4.5 $0.00001 $0.00050

Measured yesterday against content hash 7267a08d12b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check 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.

commands/check.md · 65 lines

What it actually says

/sentinel:check

Scan the current project for rule violations and generate a compliance report.

What to Do

  1. Find all source files in the project (py, ts, tsx, js, jsx, go, rs, java, c, cpp)
  2. Skip: test files, node_modules, pycache, .sentinel/, .claude/, .omc/
  3. Check each file for:
    • Standalone pass without @abstractmethod
    • raise NotImplementedError without @abstractmethod
    • TODO/FIXME/PLACEHOLDER/HACK comments
    • Hardcoded secrets (sk-, ghp_, AKIA, xoxb-)
    • print() or console.log() debug statements
    • Missing type hints (Python: def without ->)
    • Bare except: or empty catch {}
    • assert True or meaningless assertions
    • Files over 200 lines without headers
  4. Check git status for uncommitted changes
  5. Check for .sentinel/current-task.json — is there an active task?
  6. Check error log for repeated failures

Output Format

## Sentinel Compliance Report

**Project**: [project name]
**Branch**: [current branch]
**Files scanned**: [count]
**Date**: [timestamp]

### Summary
- CRITICAL violations: [count]
- HIGH violations: [count]
- MEDIUM warnings: [count]
- Files needing headers: [count]

### Violations

#### CRITICAL
- `path/to/file.py:45` — Hardcoded API key (sk-abc...)
- `path/to/views.py:12` — Bare except: pass (silent error swallowing)

#### HIGH
- `path/to/main.py:200` — Missing type hints on 5 functions
- `path/to/utils.js:30` — console.log debug statement

#### MEDIUM
- `path/to/config.py:1` — No file header (350 lines)

### Status
- Active task: [task_id or "none"]
- Uncommitted changes: [count]
- Recent errors: [summary]

### Recommendation
[Actionable next steps based on findings]
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. yesterday First seen · 65 lines · 12 tokens per session scan A 7267a08d12b4

Subscribe to this mod's changes

check is a command published in the GitHub repository tk-logl/sentinel (4 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 497 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 2026-08-31.