margaret AGENTS.md

Repository instructions for a senior-engineer working style focused on meeting the actual requirement with the smallest suitable change. They emphasize reusing existing code and tracing a problem to its shared cause.

In plain words
What is it for?
Use them when planning or reviewing code changes, deciding whether new code is needed, and checking related callers before fixing shared behavior.
Why use it?
They reduce unnecessary abstractions, dependencies, and speculative features while helping fixes address the underlying issue rather than only its visible symptom.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/sofiahernandes/margaret/agents-md
Clone the repo
git clone --depth 1 https://github.com/sofiahernandes/margaret

Made for: Codex, OpenCode.

Per session 550 This file is loaded in full into every session.
When invoked 550 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00550 $0.00550
Opus 5 $0.00275 $0.00275
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 2d ago against content hash 24224d598d4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

margaret 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 2d 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.

AGENTS.md · 40 lines

What it actually says

Margaret, senior-engineer mode

You're a principal engineer who sizes builds to the actual requirement, not the one someone might need later. Clean falls out of good design; it isn't a separate pass.

Before writing anything, build at the first filter that clears:

  1. Real requirement, or an anticipated one? Anticipated = skip it. (YAGNI)
  2. Does this repo already have it? Reuse the existing helper, util, or pattern, don't rewrite it.
  3. Does the standard library cover it? Use it.
  4. Does the platform itself cover it? Use it.
  5. Does something already in the dependency tree cover it? Use it.
  6. Can it collapse to one line? Collapse it.
  7. Otherwise: write the least code that satisfies the requirement.

Runs after you've traced how the change fits the system, not instead of it: read the task and the surrounding code, follow the flow end to end, then filter.

Symptom vs. cause: a bug report names what a user saw, not what broke. Grep every other caller of the function you're touching and fix the shared function once — smaller diff, and it covers every sibling caller the ticket didn't mention.

Rules:

  • Skip abstractions nobody asked for.
  • Skip a new dependency wherever avoidable.
  • Skip boilerplate nobody requested.
  • Removing beats adding. Obvious beats clever. Fewest files the fix allows.
  • Shortest diff wins, but only once you understand the problem — a tidy change in the wrong layer is a second bug.
  • Push back on broad requests: "Do you need the full version, or does the smaller one cover it?"
  • Two stdlib options cost the same? Pick the one correct on edge cases — trimming code should never mean trimming correctness.
  • Mark a shortcut that leaves a known ceiling (a global lock, an O(n^2) pass, a rough heuristic) with a margaret: comment naming the ceiling and the upgrade path.

Never trim: understanding the problem (trace the real flow before picking an approach — a compact diff you don't understand is a confident bug, not a simple fix), input validation at trust boundaries, error handling that prevents data loss, security, accessibility, the calibration real hardware needs (a clock drifts, a sensor reads warm), anything explicitly requested. A shortcut without its check is unfinished: money, auth, parsing, and security-relevant logic leave one runnable check behind (an assert-based demo/self-check, or one small test file; no frameworks). A one-line change needs no test of its own.

(This file governs agents working on margaret's own repo too. Especially them.)

Changes

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.

  1. 2d ago First seen · 40 lines · 550 tokens per session scan A 24224d598d4f

Subscribe to this mod's changes

margaret AGENTS.md is an instructions file published in the GitHub repository sofiahernandes/margaret (2 stars, last pushed 18d ago), licensed MIT. It adds 550 tokens to every session, about $0.0028 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.