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/phdwight/pse-edge-mcp/claude-mdgit clone --depth 1 https://github.com/phdwight/pse-edge-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/phdwight/pse-edge-mcp/claude-md)<a href="https://agentmods.dev/instructions/phdwight/pse-edge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/phdwight/pse-edge-mcp/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 | $0.00734 | $0.00734 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
pse-edge-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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
MCP server exposing Philippine Stock Exchange (PSE Edge, https://edge.pse.com.ph) data. Unofficial — Edge has no public API; we speak to the portal's own internal endpoints.
Read these first — they are the project's memory:
docs/plan.md— every design decision: scope, architecture, caching policy, auth design, delivery history, risks. Treat decided items as settled unless the user says otherwise.docs/endpoints.md— the verified endpoint map: request dialects, param names, response shapes, pagination. Trust this over guesses.
This file holds only what applies to every task. Task-specific rules (caching mechanics, auth invariants, release procedure, deploy/debug, subsystem gotchas) live in the agent memory index — load the matching topic file before working in that area.
Memory write rule: when recording a new durable instruction ("remember that…", a correction, a learned fact), create or edit the one single-purpose topic file it belongs to under the memory directory and update its line in the index. Never append to this file without asking — it is always loaded, and unchecked additions re-monolithize it.
Non-negotiable invariants
- Never refetch a cached price while the market is open (09:30–15:00 Asia/Manila,
trading days). Every upstream read goes through
FreezeService.get(..., policy=...)— never callPseEdgeClientdirectly from a tool. The default policy is the strictest, so an unlabelled read can only over-protect PSE Edge. - Tests never touch PSE Edge. All HTTP is mocked with respx against fixtures in
tests/fixtures/(recorded from real captures). A new endpoint needs a new fixture. - Loud on drift. If Edge's response shape changes, raise
EndpointChangedError— never silently return partial data. - No credentials anywhere: not in commits, image layers, ARGs, or ENV.
Architecture
server.py MCP boundary only: validate args, delegate, shape the reply.
↓
repositories.py One repository per data domain: cache key + freeze read + parse +
model. Endpoint routing lives here.
↓
service.py Freeze policy. Repositories depend on the FrozenCache protocol and
sources.py the narrow per-domain source protocols — never the concrete client.
↓
client.py Pure HTTP. parsers.py HTML/JSON → dicts.
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 · 60 lines · 734 tokens per session scan A 3c684edae797
pse-edge-mcp CLAUDE.md is an instructions file published in the GitHub repository phdwight/pse-edge-mcp (0 stars, last pushed 23d ago), licensed MIT. It adds 734 tokens to every session, about $0.0037 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
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).
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 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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.