boffin AGENTS.md

boffin AGENTS.md is an instructions file for Codex, OpenCode from MicSm/boffin. It costs 2,542 tokens per session, scanned A, a copy of boffin copilot-instructions.md, MIT.

A routing guide for ParselFire Core, which gives coding agents only the architectural rules relevant to the task instead of loading one large rule set every time.

In plain words
What is it for?
Use it when making a focused code change, or when reviewing, cleaning up, or refactoring code across the guide's staged architecture.
Why use it?
It keeps focused changes within scope and makes broad refactors or reviews systematic by requiring a read-only audit before edits.

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/micsm/boffin/agents-md
Clone the repo
git clone --depth 1 https://github.com/MicSm/boffin

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for boffin AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/micsm/boffin/agents-md.svg)](https://agentmods.dev/instructions/micsm/boffin/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/micsm/boffin/agents-md"><img src="https://agentmods.dev/badge/instructions/micsm/boffin/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,542 This file is loaded in full into every session.
When invoked 2,542 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.02542 $0.02542
Opus 5 $0.01271 $0.01271
Sonnet 5 $0.00508 $0.00508
Haiku 4.5 $0.00254 $0.00254

Measured 3d ago against content hash 5873fc36c0dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boffin 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 3d 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.

Origin

This is a copy

100% identical to boffin copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ParselFire Core Portable Routing Contract

ParselFire Core gives AI coding agents a small routed set of architectural guardrails instead of one large always-on rules dump.

Default Workflow

First match scope to the task, then pick the path:

  • Focused change (the operator asked for a specific function, fix, or feature): stay inside that scope. Make only the change requested, apply the stage guidance to what you touch, and prove it with a check. Do not scan the whole file or build a file-wide ledger; turning a scoped coding task into a file-wide refactor breaks the task boundary and gets rejected.
  • Open-ended refactor, cleanup, or review of existing code: run the two-pass audit below, scoped to what the task covers.

Two-pass audit (refactor / review / cleanup). Never fix while you are still searching; the first strong improvement you find is not the finish line.

Pass 1, Audit (read-only). Read the target across the task's scope. Walk stages S00 upward and emit a findings ledger that covers every in-scope stage, including stages with nothing to change. Do not edit anything in this pass. Use one row per finding:

path | stage | status | id | kernel | anchor | check

Columns: path the file touched; stage the S00-S06 stage; status todo, done, or skip; id the kernel id; kernel what it requires in one phrase; anchor the concrete code location the finding rests on; check the test or lint that proves it.

  • status is one of todo, done, skip, and every skip carries a reason.
  • Record every fix you name while auditing as its own row with all fields filled, and resolve it as done or skip:<reason>; never leave a fix you mentioned in reasoning off the ledger.
  • skip:clean means Pass 1 found nothing on that stage; every in-scope stage still gets a row, never an omitted one.
  • A finding you deliberately will not act on is skip:<reason> whose reason names the blocking kernel (for example, keeping a genuine special case instead of flattening it), never skip:clean.
  • A row recorded as todo resolves only to done (with its check) or skip:<reason>; never downgrade a todo to skip:clean.

Read the full file on GitHub · 187 lines

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. 3d ago First seen · 187 lines · 2,542 tokens per session scan A 5873fc36c0dc

Subscribe to this mod's changes

boffin AGENTS.md is an instructions file published in the GitHub repository MicSm/boffin (38 stars, last pushed 11d ago), licensed MIT. It adds 2,542 tokens to every session, about $0.0127 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to boffin copilot-instructions.md, differing in 0 lines, and is treated as a copy.