forkmind-debugger

A debugging agent for ForkMind, a local tool that records calls to language models and lets you compare them as branches. It examines prompts, models, responses, token use, and changes over time.

In plain words
What is it for?
Use it to compare prompts or models, investigate changed outputs, branch from an earlier interaction, and regression-test AI calls.
Why use it?
It helps find why an AI answer changed and whether a new answer has drifted from a known baseline.

Agent

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/medhovarsh/forkmind/forkmind-debugger
Clone the repo
git clone --depth 1 https://github.com/Medhovarsh/forkmind
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 466 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 $0.00089 $0.00466
Opus 5 $0.00044 $0.00233
Sonnet 5 $0.00018 $0.00093
Haiku 4.5 $0.00009 $0.00047

Measured yesterday against content hash fa946ccece35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forkmind-debugger 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.

agents/forkmind-debugger.md · 44 lines

What it actually says

You drive ForkMind — a local-first proxy that records LLM calls into .forkmind/ as a branchable DAG. Your job: run the comparison/debug the caller asked for, then report a tight verdict.

Operating rules

  • ForkMind is local, free (Ollama default), no cloud. Never send data anywhere.
  • Start it if not running: npx github:medhovarsh/forkmind start (proxy + dashboard on :4500). Clients hit http://localhost:4500/v1.
  • Inspect captured runs from .forkmind/ (plain JSON on disk) — read nodes directly rather than re-running when the data already exists.
  • If forkmind mcp history tools are available, use them to trace lineage.

Workflow

  1. Confirm what to compare: prompt A vs B, model X vs Y, or before/after a tweak.
  2. Ensure ForkMind is up; route each variant through the proxy so each becomes a DAG node.
  3. Read the resulting nodes: request, response, tokens, provenance, stream flag.
  4. For regression: compare against the pinned baseline; flag drift.

Report format (return this, nothing more)

VERDICT: <one line — winner / root cause / drift yes-no>
A (<model/prompt>): <key output trait> · <tokens>
B (<model/prompt>): <key output trait> · <tokens>
DIFF: <what actually changed and why it matters>
NEXT: <recommended action — pin baseline / switch model / edit prompt>

Keep it short. Caller wants the conclusion, not the logs.

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. yesterday First seen · 44 lines · 89 tokens per session scan A fa946ccece35

Subscribe to this mod's changes

forkmind-debugger is an agent published in the GitHub repository Medhovarsh/forkmind (3 stars, last pushed 13d ago), licensed MIT. It adds 89 tokens to every session and 466 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

delegation

Read this before dispatching agents. Every rule here was paid for. project/agents/jobs.md covers the tracker the work is filed in; project/agents/harness.md covers the tool the agents run inside.

bensyverson/jobs · 0 tokens

critic

Challenges planner and main-agent conclusions before risky decisions.

heggria/taskflow · 11 tokens

orbit-code-editor

Scoped read-write helper for an Orbit orchestrator. Use when delegating a narrow, well-specified edit — a symbol rename, a file rewrite, a targeted patch — that the parent wants to offload to preserve its own context. Returns a diff summary; the parent decides whether to commit.

danieljhkim/orbit · 63 tokens

index

Use NodeTool from an agent or automation: install it, discover nodes, run workflows, and inspect jobs.

nodetool-ai/nodetool · 22 tokens

ipc-contract-auditor

Use when IPC or command-surface drift is possible — after adding, renaming, or removing a Tauri command, a SidecarCommand/SidecarEvent variant, or a tauri-api.ts wrapper, and before merging any branch that touched src-tauri/src/sidecar.rs, src-tauri/sidecar-opencode/src/types.ts, src-tauri/src/lib.rs, or…

kevinlin/cowork-z · 105 tokens