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/tk-logl/sentinel/initgit clone --depth 1 https://github.com/tk-logl/sentinelWhat 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 | $0.00017 | $0.02335 |
| Opus 5 | $0.00009 | $0.01167 |
| Sonnet 5 | $0.00003 | $0.00467 |
| Haiku 4.5 | $0.00002 | $0.00233 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sentinel:init
Set up sentinel enforcement in the current project with guided onboarding.
Step 1: Detect Project Type
Analyze the project root to auto-detect the stack:
Check for:
pyproject.toml / setup.py / requirements.txt → Python
package.json / tsconfig.json → Node/TypeScript
go.mod → Go
Cargo.toml → Rust
pom.xml / build.gradle → Java
*.sln / *.csproj → C#/.NET
Makefile + *.c/*.cpp → C/C++
Report what was detected:
🔍 Detected: Python project (pyproject.toml found)
Linter: ruff (pyproject.toml [tool.ruff] present)
Test: pytest (pyproject.toml [tool.pytest] present)
Extensions: .py
Step 2: Create .sentinel/ Directory
.sentinel/
├── state/ # Session state archives
├── config.json # Project-specific settings
├── stats.json # Usage statistics (auto-reset per session)
└── .gitignore # Ignore runtime files
Step 3: Create .sentinel/.gitignore
# Sentinel runtime state — not committed
state/
error-log.jsonl
current-task.json
agent-results/
stats.json
Step 4: Generate .sentinel/config.json
Use detected project type to customize. Ask the user to confirm:
📋 Proposed sentinel configuration:
For Python projects:
{
"language": "auto",
"source_extensions": ["py"],
"skip_patterns": ["**/test_*", "**/*.test.*", "**/tests/**", "**/__pycache__/**"],
"header_threshold_lines": 200,
"error_repeat_limit": 3,
"enforcement": {
"pre_edit_gate": true,
"deny_dummy": true,
"surgical_change": true,
"scope_guard": true,
"secret_scan": true,
"file_header_check": true,
"env_safety": true,
"error_logger": true,
"post_edit_verify": true,
"completion_check": true,
"scope_reduction_guard": true,
"task_scope_guard": true,
"task_automark": true,
"task_completion_gate": true,
"subagent_context": true
},
"surgical_change_max_lines": 15,
"taskList": {
"enabled": true,
"file": "auto",
"idPattern": "[A-Z]+-[0-9]+",
"autoMarkOnCommit": true,
"injectOnSessionStart": true,
"maxInjectItems": 30
}
}
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 · 288 lines · 17 tokens per session scan A 7fc9bc5b73e9
init is a command published in the GitHub repository tk-logl/sentinel (4 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 2,335 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.