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/desvert/otparse-mcp/claude-mdgit clone --depth 1 https://github.com/desvert/otparse-mcpWhat 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 | $0.00806 | $0.00806 |
| Opus 5 | $0.00403 | $0.00403 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
otparse-mcp 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 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
otparse-mcp
Python environment
This project's virtual environment lives at venv/. Do not run source venv/bin/activate
— it does not persist between tool calls. Instead, invoke the venv's binaries directly:
- Run a script:
venv/bin/python script.py - Run tests:
venv/bin/pytest - Install a package:
venv/bin/pip install <package> - REPL:
venv/bin/python
Project setup
Install the package in editable mode before running tests or scripts — import otparse
will fail otherwise, even though direct python script.py invocation works without it:
venv/bin/pip install -e .
Testing conventions
- Fixtures live under
tests/fixtures/<protocol>/as small, hand-verified PCAP slices paired with a*_expected.jsonfile (the parser's own verified-correct output, used as a regression baseline — not independently hand-typed). - Before trusting any new PCAP fixture, derive ground truth independently via raw tshark
field extraction (
tshark -T fields -e ...), not by reading the parser's own output. Always confirm exact field names first withtshark -G fields | grep -i <protocol>— field names are dissector-version-specific and split across layers (e.g. Modbus:mbtcp.*vsmodbus.*; BACnet:bvlc.*vsbacnet.*(NPDU) vsbacapp.*(APDU)). - Keep fixtures small and hand-verifiable. Large/messy source PCAPs (full multi-thousand
packet captures) are reserved for a separate stress-test tier, not committed as
standard regression fixtures. Use
editcap -r <in> <out> <frame-list>to carve small slices out of larger public captures. - Run the full suite with
venv/bin/pytest tests/ -v.
Known limitations
- pyshark's JSON-based dissection omits
invoke_id/confirmed_servicefields for BACnet Error PDUs (apdu_type=5), even though raw tshark field export has them. Documented via a runtimenotesentry inparse_bacnet_pcap, not fixed.
Code conventions
- Models are pydantic (
otparse/models.py); prefer adding typed fields there over returning loosely-typed dicts. - Parsers use
_get_attr(layer, *names)to try multiple possible pyshark attribute names — but don't guess new attribute names; introspect first withdir()orfield_nameson the actual pyshark layer object when uncertain.
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.
- yesterday First seen · 67 lines · 806 tokens per session scan A c59d695cd442
otparse-mcp CLAUDE.md is an instructions file published in the GitHub repository desvert/otparse-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 806 tokens to every session, about $0.0040 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.