read-before-write

read-before-write is an agent for coding agents from pumblus/okf-harness. It costs 0 tokens per session (228 once invoked), scanned A, original, Apache-2.0.

A set of rules that tells an agent which project documents to read before writing text, running commands, changing workflows, or opening a pull request.

In plain words
What is it for?
It helps agents work safely with documentation, command-line tools, workflows, architectural decisions, and pull requests.
Why use it?
It reduces mistakes caused by using the wrong product terms, command formats, project decisions, or contribution rules.

Agent

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 agents/pumblus/okf-harness/read-before-write
Clone the repo
git clone --depth 1 https://github.com/pumblus/okf-harness

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 read-before-write

README.md
[![agentmods](https://agentmods.dev/badge/agents/pumblus/okf-harness/read-before-write.svg)](https://agentmods.dev/agents/pumblus/okf-harness/read-before-write)
Your own site
<a href="https://agentmods.dev/agents/pumblus/okf-harness/read-before-write"><img src="https://agentmods.dev/badge/agents/pumblus/okf-harness/read-before-write.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 228 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00228
Opus 5 $0.00000 $0.00114
Sonnet 5 $0.00000 $0.00046
Haiku 4.5 $0.00000 $0.00023

Measured 4d ago against content hash 1ceda8c68c34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

read-before-write 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.

docs/agents/read-before-write.md · 10 lines

What it actually says

Read before writing

Each item names the material and the branch that triggers reading it:

  • Product languageCONTEXT.md defines every product term with an Avoid list. Read it before writing any user-facing text (docs, README, issues, prompts, skill content) and use its words, never its avoid words.
  • CLI contractdocs/CLI.md documents every command and its JSON shape. Read before running or documenting okfh commands; the JSON shapes are agent contracts.
  • Workflowsdocs/WORKFLOWS.md shows the end-to-end user journeys (first useful loop, ingest, reconcile, answer, graph). Read when a change touches how people or agents use the harness.
  • Decisions and directiondocs/adr/ ADRs bind cross-package and user-visible design; docs/ROADMAP.md scopes new directions. Read both before changing cross-package behavior or proposing new features.
  • Contribution rulesCONTRIBUTING.md lists scope and PR rules. Read before opening a PR.
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. 4d ago First seen · 10 lines · 0 tokens per session scan A 1ceda8c68c34

Subscribe to this mod's changes

read-before-write is an agent published in the GitHub repository pumblus/okf-harness (34 stars, last pushed 20d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 228 tokens. 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.

Related

Other agents, from other repositories

eval-skew-reviewer

Reviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew — verifies the feature is wired into the ONE canonical ingest path AND the eval seed AND the seed liveness contract, so it can't ship "merged-but-inert". Use after changes touching ingest enrichment, a new…

7xuanlu/wenlan · 90 tokens

rust-async-safety-reviewer

Reviews Rust async code for tokio + libsql + axum concurrency hazards. Use after changes touching tokio::spawn, axum handlers, libsql connection usage, or any Send/Sync boundaries. Read-only — produces findings, does not edit.

7xuanlu/wenlan · 59 tokens

doc-drift-auditor

Read-only audit for fuzzy drift the CI teeth (driftguard.rs) cannot catch — eval numbers stale vs the current env-hash, design-doc/decision rot, memory->repo dangling pointers, and stale worktrees. Run locally on a schedule. Produces a findings report only; never edits.

7xuanlu/wenlan · 68 tokens

architect

You are the Architect. Your job is to design the plan before anyone writes code or moves files.

mishalyalin/pupsik · 0 tokens

discoverer

You are the Discoverer. Your job is to find and inventory the source material — files, data, configs, code — that will feed downstream agents (Packager, Migrator, etc.).

mishalyalin/pupsik · 0 tokens

packager

You are the Packager. Your job is to take a plan (from the Architect) and a manifest (from the Discoverer) and produce the concrete artifact — a directory, a zip, a deploy bundle.

mishalyalin/pupsik · 0 tokens