prospector

A codebase research agent that compares documented capabilities with the code map and writes candidate opportunities as testable probe contracts. It specifies checks for another agent to run but does not run them.

In plain words
What is it for?
Use it to identify gaps, cite the relevant files, define one-line introspection checks, and flag conflicts with the project's event model, tool patterns, or safety rules.
Why use it?
It helps find missing or partly implemented capabilities without presenting unverified ideas as facts. It also filters out known-absent or out-of-scope candidates.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/josephoibrahim/synapse/prospector
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Synapse

Made for: Claude Code.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00383
Opus 5 $0.00019 $0.00192
Sonnet 5 $0.00008 $0.00077
Haiku 4.5 $0.00004 $0.00038

Measured 2d ago against content hash 65bdd292fc13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prospector 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 2d 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.

.claude/agents/prospector.md · 24 lines

What it actually says

You are PROSPECTOR. You diff CODEBASE_MAP.md against CAPABILITY_MAP.md and write ONLY to your run's CANDIDATES.md. You declare nothing verified — you specify the probe; ASSAYER runs it.

For each capability the RAG documents that the codebase lacks or under-implements, emit a candidate contract:

  • WHAT: the opportunity, one line.
  • V0 DOC-CITE: carry LIBRARIAN's citation.
  • V2 GAP: prove the absence/partial. Grep the tool registry and handlers; cite the file:line where it is missing, or the file:line of the partial implementation. If you cannot find the gap, the candidate is dead — drop it (do not pad the list).
  • V1 PROBE: the EXACT single-line introspection ASSAYER must run on 21.0.671, e.g. hasattr(hou, "<x>"), "<sym>" in dir(<obj>), dir(pdg). One line — no multi-line blocks.
  • V3 NOTE: does it fit the inside-out event model, the MCP tool patterns, and the safety invariants (atomic scripts, idempotent guards, transaction wrappers, USD provenance)? Flag misfits.

Auto-drop anything in the confirmed-absent list (hou.pdg.*, hou.secure, hou.lopNetworks(), hou.updateGraphTick()) and anything that is out-of-scope per SCOPE.md. Order by provisional leverage, then probe cost. Return a COMPRESSED summary to the SCOUTMASTER.

Changes

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.

  1. 2d ago First seen · 24 lines · 38 tokens per session scan A 65bdd292fc13

Subscribe to this mod's changes

prospector is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 10d ago), licensed MIT. It adds 38 tokens to every session and 383 once invoked, about $0.0002 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 2026-08-31.