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/t-rav/hydraflow/observergit clone --depth 1 https://github.com/T-rav/hydraflowWhat 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 | $0.01079 |
| Opus 5 | $0.00012 | $0.00540 |
| Sonnet 5 | $0.00005 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
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 yesterday.
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
94% identical to observer — 1 line 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 — 138 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.
- yesterday First seen · 138 lines · 23 tokens per session scan A 6cd8475031a7
observer is an agent published in the GitHub repository T-rav/hydraflow (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 1,079 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to observer, differing in 1 line, and is treated as a copy.
Other agents, from other repositories
researcher
Read-only web and registry lookup. Use for Agent Skill / MCP discovery (npx skills find, MCP search), current-usage doc-checks, and scope source verification. Returns only a compact summary, never raw pages.
scout
Read-only code exploration and repo scanning. Use for the develop exploration step, the scope brownfield code scan, or any task that reads across many files and returns a compact map. Never edits.
explorer-rag-enhanced
MUST BE USED PROACTIVELY. Universal read-only explorer agent. Combines jrag graph navigation (call chains, service boundaries, routes, impact analysis, FQN resolution) with broad file-system search (grep, glob, excerpt reading). Use for any exploration task: locating code, tracing dependencies, finding patterns…
docs-watcher
Review code/config changes and keep all docs fresh across three altitudes — internal docs (docs/DESIGN.md WHAT/WHY, docs/ARCHITECTURE.md HOW), operator docs in docs/ (CONFIGURATION, CLI, AGENT-GUIDE, CODEBASEREQUIREMENTS, MANUAL-VERIFICATION-CHECKLIST), and the consumer skills/ + agents/ artifacts deployed verbatim to…
explorer-rag-cli
MUST BE USED PROACTIVELY. Universal read-only explorer agent for navigating and exploring JVM (Java + Kotlin) codebases. Combines graph navigation via the jrag CLI (call chains, routes, service boundaries, clients, producers, impact, FQN resolution) with jrag search (locate code/config by meaning, keywords, or natural…
perspective-generator
Use when detailed perspective analysis is needed after NCI scoring, or when high disagreement between interpretations requires synthesis. Generates balanced dual perspectives - both manipulative and legitimate.