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/briancl2/customernewsletter/agents-mdgit clone --depth 1 https://github.com/briancl2/CustomerNewsletterWrote 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/briancl2/customernewsletter/agents-md)<a href="https://agentmods.dev/instructions/briancl2/customernewsletter/agents-md"><img src="https://agentmods.dev/badge/instructions/briancl2/customernewsletter/agents-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 | $0.01051 | $0.01051 |
| Opus 5 | $0.00526 | $0.00526 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
CustomerNewsletter 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 5d 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.
AGENTS.md
Primary AI instruction surface for briancl2-customer-newsletter (platform-agnostic). Monthly GitHub customer newsletter pipeline: six core phases plus optional polish, video-enrichment, and editorial stages, driven by LLM skills, scoring, and intelligence mining.
Operating Protocol
Every change follows this numbered workflow. No exceptions.
- Hypothesize — State a testable prediction with explicit PASS criteria (HIGR)
- Score — Define a scoring rubric with acceptance threshold
- Plan — Design the approach before building
- Build — Implement the change
- Test — Validate against PASS criteria using layered scoring (cheapest first)
- Fix — Iterate until all criteria pass
- Review — Run
make reviewon ALL changes before committing.--no-verifyis NEVER permitted. - Validate — Run quality checks (scoring battery)
- Document — Update HYPOTHESES.md, LEARNINGS.md, and HANDOFF.md. For published changes, also record scope and validation in the PR description.
- Clean up — Delete old implementations (Deletion Discipline), archive stale artifacts
- Report + Handoff — Write HANDOFF.md for session continuity
Core Principles
- Deletion Discipline: Replace directly. No
_v2suffixes, no parallel code paths. - LLM-First: Agent-orchestrated workflows over deterministic scripts.
- Skills-First: Check
.github/skills/before implementing ad-hoc procedures. - HIGR: Every change is a testable hypothesis with PASS criteria.
- Trust Disk, Not Self-Reports: Verify by reading files, not trusting agent claims.
- Layered Scoring (Cheapest First): Structural → Heuristic → Selection → Editorial.
- Feed-Forward Learnings: Every finding becomes an L-number in LEARNINGS.md.
- Benchmark-Grounded: Score against benchmark data, not intuition.
Agents (4)
| # | Agent | Purpose |
|---|---|---|
| 1 | customer_newsletter | Pipeline orchestrator (phases 1A-5) |
| 2 | editorial-analyst | Editorial intelligence mining + corrections |
| 3 | skill-builder | Create and validate new skills |
| 4 | upgrade-advisor | Produce recommendation bundles from repo findings |
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.
- 5d ago First seen · 86 lines · 1,051 tokens per session scan A d286cb207022
CustomerNewsletter AGENTS.md is an instructions file published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 2mo ago), licensed MIT. It adds 1,051 tokens to every session, about $0.0053 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
agent-starter-pack GEMINI.md
Instructions for GoogleCloudPlatform/agent-starter-pack, covering agent starter pack - ai coding agent guide, core principles for ai agents, project architecture overview, 4-layer template system and key directory structure.
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
paseo CLAUDE.md
Claude Code instructions for getpaseo/paseo, covering claude.md, repository map, docs, writing docs and doc voice.
copilot copilot-instructions.md
Copilot instructions for navikt/copilot, covering copilot instructions for navikt/copilot, repository overview, nav development standards, nav principles and nav tech stack.
copilot AGENTS.md
AGENTS.md instructions for navikt/copilot, covering agents.md for navikt/copilot, what this repo is, efficiency rule, standard commands and conventions.
ai-ready AGENTS.md
AGENTS.md instructions for johnpapa/ai-ready, covering ai-ready repo — agent guide, repository structure, tech stack, build & run and testing.