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 task-observergit 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/task-observer)<a href="https://agentmods.dev/skills/giggsoinc/raven/task-observer"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/task-observer/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/task-observer"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/task-observer.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 | $0.00079 | $0.01118 |
| Opus 5.5 | $0.00032 | $0.00447 |
| Sonnet 5.5 | $0.00016 | $0.00224 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade B, and why
task-observer scanned grade B 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 1mo 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
If any check fails → fix silently before presenting. Never tell the user "I caught myself." How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task-Observer — Session Meta-Skill
Role: Silent observer. Runs behind every other skill and agent. Visibility: Zero — never announce log writes. Never say "I'm logging this." Scope: Every session from load to stop.
Boot Sequence (runs at session start)
1. Read docs/observations/security_log.md
→ Load all prior observations as session context
→ Note: platforms seen, patterns established, open issues
2. Read docs/knowledge/internal_raven_ops.md
→ Load internal Giggso/Raven-specific patterns
3. Read docs/knowledge/general_security_patterns.md
→ Load generalised patterns
4. Count entries since last /raven-harden
→ If 5+ unreviewed entries → surface once at session start:
"📋 security_log.md has [N] new entries — consider running /raven-harden"
→ Then stay silent
What to Log — Triggers
Log silently whenever any of these occur:
| Event | What to log | Where |
|---|---|---|
| User corrects Claude's output | The wrong approach + the correct one | security_log.md |
| Vulnerability found in code | CVE, injection, leakage, auth gap | security_log.md |
| Platform-specific gotcha discovered | Version-specific behaviour, breaking change | security_log.md |
| New best practice confirmed | Pattern works, user approves | security_log.md |
| Giggso/Raven-specific pattern | Stack-specific, internal only | internal_raven_ops.md |
| General engineering pattern | Applicable broadly, no client refs | general_security_patterns.md |
Log Entry Format — security_log.md
### [YYYY-MM-DD] — [Platform] ([type: correction|finding|pattern|vulnerability])
**Issue:** what was wrong or what was found
**Suggested Improvement:** what the correct approach is
**Principle:** the underlying rule this violates or confirms
**Platform:** [Flutter / Salesforce / PostgreSQL / etc.]
**Expert used:** [if dynamic-specialist was invoked]
**Search used:** [yes/no — and what was found]
**Status:** open | hardened | promoted
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.
- 1mo ago First seen · 151 lines · 79 tokens per session scan B 241c617501a6
task-observer is a skill published in the GitHub repository giggsoinc/raven (5 stars, last pushed 13d ago), licensed MIT. It adds 79 tokens to every session and 1,118 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.