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 instructions/sandeep-alluru/groundcrew/claude-mdgit clone --depth 1 https://github.com/sandeep-alluru/groundcrewWrote 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/instructions/sandeep-alluru/groundcrew/claude-md)<a href="https://agentmods.dev/instructions/sandeep-alluru/groundcrew/claude-md"><img src="https://agentmods.dev/badge/instructions/sandeep-alluru/groundcrew/claude-md.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 5.1 | $0.00224 | $0.00224 |
| Opus 5 | $0.00112 | $0.00112 |
| Sonnet 5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
groundcrew CLAUDE.md 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 5d 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.
What it actually says
groundcrew — Session Anchor
Research spec: ../tech-research/07-Computer-and-Browser-Use/groundcrew-the-deterministic-state-oracle-for-computer/README.md
One-liner: Ground-truth state oracle for computer-use agents via OS-layer (a11y tree + FS + network)
Phase: backlog
Stack: Python, pyobjc-framework-Accessibility (macOS), watchdog
Key decisions
- macOS-only for v0.1 (AXUIElement/AXObserver is mature); Linux/Windows deferred
Next step
Read the research spec, then implement the macOS AXUIElement state snapshot daemon.
MVP definition
pip install groundcrewworks- Python daemon reading macOS AXUIElement + watchdog/FSEvents → structured JSON snapshots
- CLI:
groundcrew capture <script>wraps any Python script and emits before/after "action receipt" - Structured JSON diff showing: accessibility tree delta + filesystem change
- README with example action receipt output
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.
- 5d ago First seen · 21 lines · 224 tokens per session scan A 12363e14707d
groundcrew CLAUDE.md is an instructions file published in the GitHub repository sandeep-alluru/groundcrew (0 stars, last pushed 19d ago), licensed MIT. It adds 224 tokens to every session, about $0.0011 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 instructions, from other repositories
activity-frames AGENTS.md
Instructions for nossa-y/activity-frames, covering can i install it without asking?, the mental model (10 seconds), fastest integration: mcp, from python and things you should not do.
pi AGENTS.md
AGENTS.md instructions for TGYD-helige/pi, covering pi extensions monorepo — agent guidelines, project overview, required agent skills, ponytail — minimal-code discipline and mattpocock/skills — engineering workflow skills.
open-computer-use CLAUDE.md
Claude Code instructions for Wide-Moat/open-computer-use, covering project instructions, branches and scope, global rules (apply to every branch), language and license headers.
clickproof CLAUDE.md
Claude Code instructions for sandeep-alluru/clickproof, covering clickproof — session anchor, key decisions, next step and mvp definition.
oraclemcp AGENTS.md
Instructions for MuhDur/oraclemcp, covering agents.md - oraclemcp, rule 1 - absolute, irreversible / outward-facing actions, swarm operating constitution and rust toolchain & gates.
telos AGENTS.md
AGENTS.md instructions for HarperZ9/telos, covering telos agent instructions, scope, developer contract and verification.