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 agents/sangrokjung/claude-forge/observergit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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/sangrokjung/claude-forge/observer)<a href="https://agentmods.dev/agents/sangrokjung/claude-forge/observer"><img src="https://agentmods.dev/badge/agents/sangrokjung/claude-forge/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 | $0.00023 | $0.01094 |
| Opus 5 | $0.00012 | $0.00547 |
| Sonnet 5 | $0.00005 | $0.00219 |
| Haiku 4.5 | $0.00002 | $0.00109 |
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 4d 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 — 139 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 significant session activity (20+ tool calls)
- When user runs
/analyze-patterns - On a scheduled interval (configurable, default 5 minutes)
- When triggered by observation hook (SIGUSR1)
Input
Reads observations from ~/.claude/homunculus/observations.jsonl:
{"timestamp":"2025-01-22T10:30:00Z","event":"tool_start","session":"abc123","tool":"Edit","input":"..."}
{"timestamp":"2025-01-22T10:30:01Z","event":"tool_complete","session":"abc123","tool":"Edit","output":"..."}
{"timestamp":"2025-01-22T10:30:05Z","event":"tool_start","session":"abc123","tool":"Bash","input":"npm test"}
{"timestamp":"2025-01-22T10:30:10Z","event":"tool_complete","session":"abc123","tool":"Bash","output":"All tests pass"}
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"
4. Tool Preferences
When certain tools are consistently preferred:
- Always uses Grep before Edit
- Prefers Read over Bash cat
- Uses specific Bash commands for certain tasks
→ Create instinct: "When needing X, use tool Y"
Output
Creates/updates instincts in ~/.claude/homunculus/instincts/personal/:
---
id: prefer-grep-before-edit
trigger: "when searching for code to modify"
confidence: 0.65
domain: "workflow"
source: "session-observation"
---
# Prefer Grep Before Edit
## Action
Always use Grep to find the exact location before using Edit.
## Evidence
- Observed 8 times in session abc123
- Pattern: Grep → Read → Edit sequence
- Last observed: 2025-01-22
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.
- 4d ago First seen · 139 lines · 23 tokens per session scan A 6eb1e64adabe
observer is an agent published in the GitHub repository sangrokjung/claude-forge (822 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,094 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
strategic-advisor
Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
ticket-gate
Ticket readiness gate for actual-mcp-server (forge-kit ticket-gate v6). Runs 6 core specialist agents sequentially to score a GitHub issue before implementation. Each agent scores 1-10; ALL must score 10 to pass. An agent whose domain the ticket does not touch auto-scores 10 (N/A). Extra specialists are added by…
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.