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 msdakot/ai-foundary --skill skill-observergit clone --depth 1 https://github.com/msdakot/ai-foundaryWrote 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/msdakot/ai-foundary/skill-observer)<a href="https://agentmods.dev/skills/msdakot/ai-foundary/skill-observer"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/skill-observer.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 5.1 | $0.00038 | $0.00569 |
| Opus 5 | $0.00019 | $0.00284 |
| Sonnet 5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade B, and why
skill-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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/observer/pending-suggestions.jsonl 2>/dev/null || echo "No pending suggestions." 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.
Skill Observer — Suggestion Review
The background observer watches conversation turns and flags repeated correction patterns. This skill lets the user review and act on those findings.
Step 1 — Read pending suggestions
cat ~/.claude/observer/pending-suggestions.jsonl 2>/dev/null || echo "No pending suggestions."
If empty, tell the user: "No suggestions pending. The observer will flag patterns as they accumulate across sessions."
Step 2 — Present each finding clearly
For each entry in the file, show the user:
┌─ Suggestion ─────────────────────────────────────────────────────┐
│ Type: <claude-md | new-skill | patch-skill> │
│ Theme: <theme> │
│ Confidence: <high | medium | low> │
│ Evidence: <evidence> │
│ │
│ Proposed: <suggestion text> │
└──────────────────────────────────────────────────────────────────┘
Ask: "Apply this suggestion? [y]es / [n]o / [e]dit"
Step 3 — Act on user response
y — approve:
claude-md: append the suggestion text as a bullet to~/.claude/CLAUDE.md. Create the file if it doesn't exist.new-skill: create a new SKILL.md at~/.claude/skills/<slugified-theme>/SKILL.mdwith the suggestion as the body. Tell the user to register it in their settings if needed.patch-skill: show the user which skill file to edit, display the suggested change, and apply it if they confirm.
n — reject:
- Mark dismissed. Do not apply.
e — edit:
- Show the suggestion text in full, let the user dictate changes, then apply the edited version.
Step 4 — Clear applied/rejected suggestions
After processing all suggestions, remove handled entries from the pending file:
# Clear the file after all suggestions are resolved
> ~/.claude/observer/pending-suggestions.jsonl
What ships with it
2 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.
- 7d ago First seen · 65 lines · 38 tokens per session scan B 2cd520226f1b
skill-observer is a skill published in the GitHub repository msdakot/ai-foundary (5 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 569 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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…
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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…