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/deeplink-org/probing/agents-mdgit clone --depth 1 https://github.com/DeepLink-org/probingWhat 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 | $0.03615 | $0.03615 |
| Opus 5 | $0.01808 | $0.01808 |
| Sonnet 5 | $0.00723 | $0.00723 |
| Haiku 4.5 | $0.00362 | $0.00362 |
Grade A, and why
probing AGENTS.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 3d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions — probing
This repository uses the Agent Skills layout for training diagnostics.
Module boundaries
Before adding code, read docs/src/design/modularity.md (中文: modularity.zh.md).
| Layer | Where | Your change belongs if… |
|---|---|---|
| L1 Platform | probing/core, memtable, proto |
SQL engine, federation, storage format |
| L2 Collectors | probing/extensions/*, python/probing/profiling |
New metrics / tables |
| L3 Control | probing/server, probing/cli |
HTTP, inject, fan-out |
| L4 Experience | skills/, web/, Python hooks |
Diagnostics UX, skills, UI |
Contracts: ProbeDataSource (tables), ProbeExtension (config/HTTP), @table (Python data), skills/*/steps.yaml (workflows). Do not add cross-collector calls — use SQL JOINs.
Coding principles
These rules extend docs/src/design/modularity.md. Read that doc for layer ownership and dependency direction; follow the rules below on every change.
Minimal diff (pragmatic)
- Solve the stated problem only. No cross-module drive-by refactors, renames, or formatting.
- In touched files, necessary follow-on edits are OK — fix what the change breaks in the same module; do not expand scope to unrelated modules.
- One concern per PR. A bug fix should not also add a feature; a skill SQL tweak should not also change server routing.
- Composition stays at the root. New wiring belongs in
probing/server/src/engine.rs(or the relevant composition root), not sprinkled across L2 collectors. - Prefer under 500 lines diff. Larger PRs need a short justification in the description.
Refactoring in the same PR is allowed only when under 50 lines and confined to one module/crate. Larger refactors → separate PR first.
High cohesion, low diffusion
Each crate / directory owns one concern end-to-end. Default: ≤2 modules/crates per PR. A third module is OK with justification in the PR description.
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.
- 3d ago First seen · 270 lines · 3,615 tokens per session scan A 3b6c3d3a354a
probing AGENTS.md is an instructions file published in the GitHub repository DeepLink-org/probing (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,615 tokens to every session, about $0.0181 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 2026-08-30.
Other instructions, from other repositories
webperf-snippets CLAUDE.md
Instructions for nucliweb/webperf-snippets, covering claude.md, project overview, architecture, technology stack and project structure.
VeloQ AGENTS.md
Instructions for lucifer1004/VeloQ, covering veloq — contributor guidelines, wire-format invariants (do not break casually), workspace layout, shipped commands (status roadmap) and code conventions.
etw-mcp CLAUDE.md
Instructions for nijosmsft/etw-mcp, covering claude.md, what this repo is, layout, how tools get registered and trace lifecycle.
uniprof CLAUDE.md
Instructions for indragiek/uniprof, covering uniprof codebase guide, project layout, quick start, cli reference and aliases & parsing.
coz CLAUDE.md
Claude Code instructions for plasma-umass/coz, covering claude.md, project overview, why causal profiling?, build system and building coz.
cpp-analysis-mcp CLAUDE.md
Claude Code instructions for GusDawn123/cpp-analysis-mcp, covering claude.md — how this repo is worked, read first, always, source control (non-negotiable), the working ritual (per sub-chunk, six steps, no skipping) and clean habits.