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 skills add giggsoinc/raven --skill raven-coregit 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/skills/giggsoinc/raven/raven-core)<a href="https://agentmods.dev/skills/giggsoinc/raven/raven-core"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/raven-core/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/giggsoinc/raven/raven-core"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/raven-core.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.00862 |
| Opus 5 | $0.00023 | $0.00431 |
| Sonnet 5 | $0.00009 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
raven-core 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raven Core
Live Config
!cat .raven/manifest.json 2>/dev/null || echo "MANIFEST MISSING — run raven-setup.sh"
Step 0 — Prompt Analysis (fires on EVERY prompt before anything else)
Read the incoming prompt. Detect intent. Route accordingly.
| If prompt mentions... | Route to | Action |
|---|---|---|
| "find skill" / "search skill" / "what skill" | /raven-search {query} |
Run skill search |
| "expert" / "L99" / "deep dive" / "world class" | raven-expert |
Activate L99 mode |
| "security" / "threat model" / "vulnerability" / "CVE" | raven-security |
Security review |
| "plan" / "phases" / "architecture first" / "scaffold" | raven-plan + /raven-scaffold |
Force plan before code |
| "review" / "PR" / "code review" | raven-review |
Manifest-aware review |
| "refactor" / "clean up" / "too long" | raven-refactor |
Style enforcement |
| "test" / "write tests" / "coverage" | raven-test |
Test-first |
| "document" / "docstring" / "README" | raven-document |
Doc enforcement |
| "drama" / "debate" / "stress-test" / "panel" | andie Drama Mode |
Expert panel |
| JSX / React / npm / node_modules in prompt | WARN + block | "Raven: manifest forbids this framework" |
new import X in code |
CVE check | cve-check.py --library X |
| "commit" / "push" / "git add" | Pre-commit gate | All 5 checks fire |
| "sync libraries" / "requirements changed" / "new dependency" | /raven-sync |
Auto-sync requirements → manifest |
| no specific match | passive mode | Style + stack rules apply |
Step 1 — Project context
!cat .raven/manifest.json 2>/dev/null | python3 -c "import json,sys; d=json.load(sys.stdin); print('Project:', d.get('project'), '| Mode:', d.get('mode','team'), '| Lang:', d.get('stack',{}).get('language'))" 2>/dev/null || true
Step 2 — Project-specific rules
!cat .raven/manifest.json 2>/dev/null | python3 -c " import json,sys d=json.load(sys.stdin) rules=d.get('project_rules',{}) ff=rules.get('forbidden_frameworks',[]) if ff: print('FORBIDDEN frameworks:', ', '.join(ff)) lic=rules.get('license','') if lic: print('License header required:', lic) cc=rules.get('commit_convention','') if cc: print('Commit convention:', cc) ag=rules.get('require_approval_gates',False) if ag: print('Approval gates: REQUIRED before any file write') " 2>/dev/null || true
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 65 lines · 47 tokens per session scan A 0ac9388d8373
raven-core is a skill published in the GitHub repository giggsoinc/raven (5 stars, last pushed 8d ago), licensed MIT. It adds 47 tokens to every session and 862 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…