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/giggsoinc/raven/raven-initgit clone --depth 1 https://github.com/giggsoinc/ravenWrote 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/giggsoinc/raven/raven-init)<a href="https://agentmods.dev/commands/giggsoinc/raven/raven-init"><img src="https://agentmods.dev/badge/commands/giggsoinc/raven/raven-init.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 | $0.00026 | $0.01839 |
| Opus 5 | $0.00013 | $0.00920 |
| Sonnet 5 | $0.00005 | $0.00368 |
| Haiku 4.5 | $0.00003 | $0.00184 |
Grade A, and why
raven-init scanned grade A with 1 finding 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 5d 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.
Asks the agent to reveal its instructionslowSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
5. Output instructions: Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/raven init
Initializes Raven for a new project by generating a validated manifest.json interactively.
Run this command when starting a new project. It will ask you questions, generate the manifest, validate it against the schema, and commit it to Git with a proper audit trail entry.
Pre-checks
-
Is
.raven/manifest.jsonalready present?- YES → Load it. Trust it. Proceed with the declared stack. Do not ask to reinitialize. Do not modify it unless the user explicitly requests a change.
- NO → Greenfield. Run interactive creation below.
-
(Greenfield only) Is Git initialized?
- NO → Warn: "Git not initialized. Run
git initfirst. Audit trail requires Git."
- NO → Warn: "Git not initialized. Run
Greenfield Creation Rules
NEVER auto-detect or pre-populate answers from:
- existing venv or .venv directories
- requirements.txt / pyproject.toml / package.json
- .env files or environment variables
- any other project files on disk
Every answer comes from the user. No exceptions.
The manifest is what the user declares — not what the project happens to contain.
Interactive Questions
Ask these questions one at a time. Wait for answer before proceeding.
Question 1 — Project name:
What is your project name?
(letters, numbers, hyphens only — e.g. PatronAI, trinity-v2, genlock)
Validate: matches pattern ^[a-zA-Z0-9_-]+$
If invalid → re-ask with example.
Question 2 — Work type:
What kind of work is this project?
( ) code — writing application code (Python, TypeScript, Go, etc.)
( ) infra — infrastructure only (Terraform, K8s YAML, CloudFormation, Helm)
( ) review — reviewing code, docs, or architecture (no new files generated)
( ) mixed — both code and infrastructure in the same project
Single select. This determines which validators apply.
- code → full language + library validation
- infra → no language block on .yaml/.yml/.tf/.hcl/.json files
- review → stack validation skipped entirely (read-only work)
- mixed → code rules for .py/.ts/.go, infra rules for .yaml/.tf/.hcl
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.
- 5d ago First seen · 317 lines · 26 tokens per session scan A 80069017a2c4
raven-init is a command published in the GitHub repository giggsoinc/raven (5 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 1,839 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). 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.