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/emaraschio/cursor-commands/pathfindergit clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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/emaraschio/cursor-commands/pathfinder)<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/pathfinder"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/pathfinder.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 | $0.00045 | $0.00916 |
| Opus 5 | $0.00023 | $0.00458 |
| Sonnet 5 | $0.00009 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
pathfinder 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Map a project's uncertainty before building. Given a goal and known context, produce a six-section fog map: decisions already fixed, decision frontiers, fog-of-war questions, a next move per unknown, a parallel work plan, and the next three actions. Plan-only. Does not execute the project in the same turn. Full workflow: .cursor/skill-contracts/pathfinder/SKILL.md (user install: ~/.cursor/skill-contracts/pathfinder/SKILL.md).
Defaults
| Setting | Default |
|---|---|
| Deliverable | Six-section fog map in chat |
| Execution | None in same turn (follow-up track, or define-agent-goal) |
| Ambiguity | Clarify the goal and separate fixed from unknown before drafting |
| Next-move labels | research, prototype, ask an expert, user test, delegate |
| Examples | Generic names only (service-a, repo1) |
Steps
- Read
.cursor/skill-contracts/pathfinder/SKILL.mdfor the full agent contract; if that file is missing, read~/.cursor/skill-contracts/pathfinder/SKILL.md. - Execute phases in order (Intake -> Discovery -> Draft the map -> Deliver); do not skip discovery or start building the project.
- Report the fog map (sections 1 to 6); offer optional save under
docs/decision-maps/when the host hasdocs/.
Anti-patterns
- Separate fixed from unknown. Trigger: drafting the "decisions already fixed" section. Wrong: listing an assumption as a settled decision. Correct: mark a decision fixed only when the context states it; An assumption is not a fixed decision, so keep assumptions in frontiers or fog. Reason: false certainty hides the real risk and sends the project building on ground that was never solid.
- Tag every unknown with a next move. Trigger: listing fog-of-war questions. Wrong: leaving an unknown with no resolution path. Correct: label each unknown with exactly one next move (research, prototype, ask an expert, user test, or delegate). Reason: an unknown with no next move never gets resolved and resurfaces mid-build.
- Deliver the map without building it. Trigger: finishing the map for a project whose next step looks obvious. Wrong: scaffolding code or running destructive commands in the same turn. Correct: stop at the map (plan-only) unless the user explicitly says to skip planning and build now. Reason: this skill is plan-only, and building on unmapped fog is exactly the failure it exists to prevent.
- Parallel tracks and three actions. Trigger: filling the parallel work plan and next-actions sections. Wrong: a single-thread plan or vague next steps. Correct: 3 to 5 parallel tracks plus exactly three concrete actions today. Reason: a map without parallelizable work and concrete next steps fails to unlock progress.
- Docs save only after confirm. Trigger: host has a
docs/directory and the map is ready. Wrong: writingdocs/decision-maps/...unprompted. Correct: offer the path and write only after the user confirms. Reason: unsolicited docs clutter the host workspace. - Do not claim a native product feature. Trigger: describing what this deliverable is. Wrong: implying a built-in Cursor product feature. Correct: present this as a portable planning document for Cursor agents. Reason: a native-product claim misleads the user about what shipped.
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 · 49 lines · 45 tokens per session scan A 777b0be14fff
pathfinder is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 28d ago), licensed MIT. It adds 45 tokens to every session and 916 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.
Other commands, from other repositories
grok_init
Discover, verify, and persist the local HTTP proxy used by Grok Build Supervisor.
analyze-deps
Analyze the project's dependency tree, identify unused or duplicate dependencies, and suggest optimizations.
security-audit
Perform a security-focused review of the code I've @-mentioned (or the most relevant changes in this conversation).
fix-issue
Command "fix-issue" from HKTITAN/cursor-best-practices, covering steps and rules.
run-tests-and-fix
Run the project's test suite, fix any failures, and report what changed.
update-deps
Update the project's dependencies and ensure the project still works.