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.
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/agents/aaaaqwq/agi-super-team/observer)<a href="https://agentmods.dev/agents/aaaaqwq/agi-super-team/observer"><img src="https://agentmods.dev/badge/agents/aaaaqwq/agi-super-team/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/agents/aaaaqwq/agi-super-team/observer"><img src="https://agentmods.dev/badge/agents/aaaaqwq/agi-super-team/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 | $0.00033 | $0.01883 |
| Opus 5.5 | $0.00013 | $0.00753 |
| Sonnet 5.5 | $0.00007 | $0.00377 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
observer 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 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.
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.
This is a copy
100% identical to observer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observer Agent
A background agent that analyzes observations from Claude Code sessions to detect patterns and create instincts.
When to Run
- After enough observations accumulate (configurable, default 20)
- On a scheduled interval (configurable, default 5 minutes)
- When triggered on demand via SIGUSR1 to the observer process
Input
Reads observations from the project-scoped observations file:
- Project:
~/.claude/homunculus/projects/<project-hash>/observations.jsonl - Global fallback:
~/.claude/homunculus/observations.jsonl
{"timestamp":"2025-01-22T10:30:00Z","event":"tool_start","session":"abc123","tool":"Edit","input":"...","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:01Z","event":"tool_complete","session":"abc123","tool":"Edit","output":"...","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:05Z","event":"tool_start","session":"abc123","tool":"Bash","input":"npm test","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:10Z","event":"tool_complete","session":"abc123","tool":"Bash","output":"All tests pass","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
Pattern Detection
Look for these patterns in observations:
1. User Corrections
When a user's follow-up message corrects Claude's previous action:
- "No, use X instead of Y"
- "Actually, I meant..."
- Immediate undo/redo patterns
→ Create instinct: "When doing X, prefer Y"
2. Error Resolutions
When an error is followed by a fix:
- Tool output contains error
- Next few tool calls fix it
- Same error type resolved similarly multiple times
→ Create instinct: "When encountering error X, try Y"
3. Repeated Workflows
When the same sequence of tools is used multiple times:
- Same tool sequence with similar inputs
- File patterns that change together
- Time-clustered operations
→ Create workflow instinct: "When doing X, follow steps Y, Z, W"
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 · 199 lines · 33 tokens per session scan A 654f2f0fc9d9
observer is an agent published in the GitHub repository aAAaqwq/AGI-Super-Team (109 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,883 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to observer, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
knowledge-extractor
Extracts reusable patterns, pitfalls, and decisions from completed work and writes them to the wiki staging area. Run after finishing a body of work to capture what was learned. Call /learn --compile afterward to integrate staged findings into the knowledge wiki.
Pamięc cross-fazowa systemu
Syntetyk to agent strategiczny którego jedynym zadaniem jest utrzymywanie MANIFEST.md jako Single Source of Truth. Zbiera wyniki z każdej fazy, dokumentuje decyzje architektoniczne, flaguje sprzeczności między agentami i wyciąga wnioski cross-funkcyjne których pojedynczy specjalista nie zobaczy.
cko
Chief Knowledge Officer — VP-level vault governance and institutional memory quality gate. Use to review and approve/reject vault note admissions (post-Guardian structural QC), enforce knowledge strategy and memory policy, allocate tokens to memory creators, and govern token cost vs. utility. Auto-spawns weekly…
context-engineer
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
rlm-cleanup-agent
Cleans the RLM summary cache by removing entries for files that no longer exist on disk. Trigger when the user says "clean the RLM cache", "remove stale summaries", "the RLM cache has entries for deleted files", or "prune outdated RLM entries". user: "The RLM cache has summaries for files I deleted" assistant: "I'll…
rlm-init
Initializes the RLM cache for an existing project — creates rlmprofiles.json, scans configured directories, and runs the first distillation pass. Trigger when the user says "initialize RLM", "set up RLM for this project", "create the RLM profile", or "first-time RLM setup". For a guided wizard experience use the…