Borrowing it
Nothing to install: this file belongs to edgedepthhq/edgedepth-research-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/edgedepthhq/edgedepth-research-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/edgedepthhq/edgedepth-research-mcpWrote 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/edgedepthhq/edgedepth-research-mcp/claude-md)<a href="https://agentmods.dev/instructions/edgedepthhq/edgedepth-research-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/edgedepthhq/edgedepth-research-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/edgedepthhq/edgedepth-research-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/edgedepthhq/edgedepth-research-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01179 | $0.01179 |
| Opus 5.5 | $0.00472 | $0.00472 |
| Sonnet 5.5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
edgedepth-research-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 15d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
edgedepth-research-mcp: project instructions
Read ../todos-edgedepth/PRIORITIES.md for shared engineering policy, goals,
task lifecycle, and production boundaries, then ../todos-edgedepth/TASKS.md
and the matching task before project work.
Read README.md for tool semantics, auth, transports, and development checks.
Preserve research-only behavior, explicit metering, missing-data states, and
canonical evidence. Load web or backend context only for a contract crossing.
Daily crossing condition (2026-10-02, local)
The registry-driven tools accept feature.price_oi_ratio_cross_5m_v1 once the
research engine and web registry are released. No new tool or feature allowlist
is needed. Contract mirror and in-memory list_features protocol test are updated;
these are not production MCP reads. Historical Binance, five-minute closes,
00:05 UTC daily reference; no live monitoring. Record scans retain one-hour match
spacing, whereas prevalence counts raw crossing closes. See backend
docs/RESEARCH_RATIO_CROSSINGS.md. No re-extraction or +5% study is part of this work.
Private Radar hypotheses (2026-10-02, local)
get_hypothesis / prepare_hypothesis / save_hypothesis / run_hypothesis share web's account-owned private history. Admin pilot only. Optional research:hypotheses permission is required for writes; read + interpret defaults remain unchanged. Web and its optional key-scope enum migration precede MCP. Exact human-approved four-request plans execute serially through returned continuations. Stop on absence/refusal/unknown completion; reopening never retries. Preserve negative attempts, missingness, native denominators, receipts and reserved-date boundaries. No evaluation-period execution, alerts, trades, publication or deployed claim. See README private workflow and web docs/RADAR_HYPOTHESES.md.
Shared saved assessment (2026-10-03, local)
get_investigation_assessment reads the web-owned released assessment and exact scope/evidence metadata. No model, compute, new publication or private draft access. Preserve 409 edition-change and 410 correction refusals. Deploy web reader first. Tests: investigation-assessment and tool schema; current release version is unchanged until an authorized release. Owner: research-surface-usability.
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.
- 15d ago Changed · +45 lines · +683 tokens per session 519bca927f9c
- 24d ago Changed · +9 lines · +92 tokens per session 7a3df70d6456
- 25d ago Changed · +22 lines · +296 tokens per session 093a1d310e03
- 1mo ago First seen · 10 lines · 108 tokens per session scan A 6c70988a8fb8
edgedepth-research-mcp CLAUDE.md is an instructions file published in the GitHub repository edgedepthhq/edgedepth-research-mcp (3 stars, last pushed 15d ago), licensed MIT. It adds 1,179 tokens to every session, about $0.0047 per session on Opus 5.5. 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 2026-09-06.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.