Borrowing it
Nothing to install: this file belongs to Political-Comms/political-comms-sdk. 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/Political-Comms/political-comms-sdk/main/AGENTS.mdgit clone --depth 1 https://github.com/Political-Comms/political-comms-sdkWrote 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/political-comms/political-comms-sdk/agents-md)<a href="https://agentmods.dev/instructions/political-comms/political-comms-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/political-comms/political-comms-sdk/agents-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/political-comms/political-comms-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/political-comms/political-comms-sdk/agents-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 | $0.00529 | $0.00529 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
political-comms-sdk 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 6d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Political Comms SDK - Agent Instructions
This repo holds the official Political Comms client packages:
packages/sdk- TypeScript SDK (@political-comms/sdk, npm)packages/cli- CLI (@political-comms/cli, npm)packages/mcp- MCP server (@political-comms/mcp, npm)python/- Python SDK (political-comms, PyPI)
The public API surface these clients wrap is defined by the OpenAPI spec maintained in the political-comms-docs sibling repo (api-reference/openapi.json). When the API changes in political-comms-app, every package here must be updated to match - types, methods, docs, and version bumps. Publishing to npm/PyPI is owner-executed; prepare the release, don't push it.
Email surface (early access)
All four packages wrap the 40 /v1/email operations (domains, senders, lists,
imports, suppressions, templates, drafts, campaigns) added by DEV-654. Every one of them returns
403 EMAIL_EARLY_ACCESS until the email product reaches general availability,
so each method, tool, and command must say so in its docstring or description.
Email lists are keyset paginated ({ data, has_more, next_cursor }), unlike the
older messaging endpoints, which return plain arrays. There is no inbound email
or inbox surface, and no A/B testing: do not add methods for either.
The MCP email surface is reads, the campaign lifecycle, and the two writes that
spend money or add contacts (create_email_template_draft,
start_email_list_import), both behind confirm: true. It exposes no delete
tools, which is what keeps the "no destructive operations" property the server
test asserts. Template create, update, and delete stay off the MCP surface:
authoring HTML belongs in a script against the SDK.
Cross-layer standard
This repo is one of six layers of the Political Comms platform (app frontend/backend, public docs, marketing site, pccampaigns-site, this SDK repo, agents repo). Every task ends with a surface sweep: changes elsewhere (especially the public API) must land here, and SDK changes may ripple to docs and the agents repo. The canonical rule and ripple-chain table live in ../political-comms-app/AGENTS.md, section "Cross-Layer Surface Sweep". Working across all sibling repos is standing policy - don't ask per-repo.
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.
- 6d ago First seen · 32 lines · 529 tokens per session scan A 5f9277348044
political-comms-sdk AGENTS.md is an instructions file published in the GitHub repository Political-Comms/political-comms-sdk (0 stars, last pushed 2d ago), licensed MIT. It adds 529 tokens to every session, about $0.0026 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 2026-09-04.
Other instructions, from other repositories
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.
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).
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.
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.