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 commands/marcosd4h/deepextractruntime/hunt-plangit clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimeWrote 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/commands/marcosd4h/deepextractruntime/hunt-plan)<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/hunt-plan"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/hunt-plan.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 | $0.00000 | $0.03577 |
| Opus 5 | $0.00000 | $0.01788 |
| Sonnet 5 | $0.00000 | $0.00715 |
| Haiku 4.5 | $0.00000 | $0.00358 |
Grade A, and why
hunt-plan 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunt Plan
Overview
Hypothesis-driven vulnerability research planning and strategic campaign design. Generates testable attack hypotheses, matches observations to known Windows attack patterns, plans variant analysis, validates suspected findings, and maps trust boundaries -- all mapped to concrete workspace commands. Also covers strategic planning at the campaign, cross-module, and replan levels.
The command supports 4 modes selected by the first argument:
/hunt-plan appinfo.dll-- campaign mode (default): plan a full VR campaign (includes trust boundary mapping)/hunt-plan hypothesis TOCTOU appinfo.dll-- test a specific vulnerability hypothesis, find variants of a pattern, or validate a suspected finding/hunt-plan cross appinfo.dll consent.exe-- plan a cross-module taint and data flow campaign/hunt-plan replan-- re-plan from prior analysis results
If no arguments are provided, ask the user what they want to investigate.
IMPORTANT: Execution Model
This is a collaborative dialogue command. Do NOT run analysis, write code, or execute scripts. The purpose is to produce an approved research design with testable hypotheses that transitions into an implementation plan via CreatePlan. All investigation happens after the user approves.
Steps
1. Detect mode
Parse the user's input to determine the research mode:
| First argument | Mode | Description |
|---|---|---|
| (module name only) | campaign |
Plan a full VR campaign against the module (includes trust boundary mapping) |
hypothesis |
hypothesis |
Formulate and test a hypothesis, find pattern variants, or validate a suspected finding |
cross |
cross-module |
Plan a cross-module taint and data flow investigation |
replan |
replan |
Re-plan based on prior analysis results |
Default to campaign when only a module name is provided.
2. Gather existing context
Check what data is already available before asking questions:
- Review session context for available modules and module profiles
- Check
.claude/cache/and.claude/workspace/for prior triage, classification, or attack surface results - Note which modules have been analyzed and what data exists
- If a specific module is mentioned, check whether
/triageoutput exists
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 · 330 lines · 0 tokens per session scan A 0337a3379312
hunt-plan is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (19 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,577 tokens. 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.