Skip to content
Dev Text Forge
Start free

Technical writing, fixed in one pass

Write it in your English. Ship it in native technical English.

Dev Text Forge rewrites PR descriptions, docs, commit messages and agent context files into clear, precise English, then checks the result with deterministic gates so no path, flag, identifier or number goes missing.

Rewrite your first text free See pricing
  • Free plan with no card. Sign in with Google in one click.
  • Not a chatbot: one job, a versioned pipeline, gates you can read.
  • Fixes apply to the draft only. Your saved source is never modified.
Dev Text Forge workbench: a rough PR description, its optimized rewrite and the quality gate findings
Dev Text Forge workbench: a rough PR description, its optimized rewrite and the quality gate findings. Real product screen.

Why it matters now

Your words are now instructions, and they cost tokens.

Reviewers skim a PR description that rambles, and coding agents read every word of AGENTS.md on every run. Unclear sentences waste their time; padded ones waste your context window. Rewriting by hand is slow, and a generic AI rewrite can silently drop the one flag that mattered.

50–90%

lower long-context cost reported from caching, compression and context engineering, which starts with saying the same thing in fewer tokens.

Source: Zylos Research, LLM context management (2026)

Paste, optimize, review, save

  1. 01

    Paste or upload

    Drop in Markdown or plain text: a PR, an issue, API docs, a commit message, an AGENTS.md.

  2. 02

    Pick a mode

    Prose for native-level English, Structured prompt for a tagged skeleton, or Agent context for files coding agents read.

  3. 03

    Review the gates

    Fidelity, rules, structure, length and schema checks run on every output and point to the exact line.

  4. 04

    Save with history

    Save explicitly, keep every version, and compare source and output side by side.

A rewrite you can trust because it is checked

The model writes; non-LLM gates verify. Every finding links to its line, and every fix changes only the draft.

Quality gates

Nothing technical gets lost in translation

The fidelity gate checks that every code span, path, URL, identifier and number in your input survives into the output, and flags the ones that changed, like 5000 becoming 5,000.

  • Rules: no emojis, bold-as-heading or questions to the reader
  • Structure: headings at ## and ###, only code inside fences
  • Length: flags output that looks truncated
Dev Text Forge workbench: a rough PR description, its optimized rewrite and the quality gate findings

Agent context modePro

Put your AGENTS.md on a token diet

Rewrite AGENTS.md, CLAUDE.md and similar files into short, imperative rules agents follow, and see the token count before and after with a list of every change.

  • Keeps commands, paths and code blocks intact
  • Change report: rules rewritten, repeats removed, what went missing
  • Batch optimize many files at once
Agent-context mode rewriting an AGENTS.md, with the token diet and the list of changes

For developers who think in code and write in a second language

Plenty of strong engineers write software in English as a second language. Dev Text Forge closes the gap without taking the technical details away.

A developer writes technical documentation at his home-office desk in the evening
Developers write the PR the way they think, then ship a description reviewers can skim.
A remote developer smiles while presenting a pull request on a video call
Remote teams present changes with docs that read the same in every timezone.
A technical writer and a backend engineer edit a document together at a shared monitor
Writers and engineers agree on wording without losing a single flag or path.

Photos are AI-generated illustrations, not customers.

Fix a message before you hit send

On a phone the source and output stack vertically, so you can rewrite a commit message or a reply from anywhere.

The Dev Text Forge workbench on a phone with stacked source and output panes

a DevSpeak Labs product

One plan, four apps.

Dev Text Forge is one of four DevSpeak Utilities apps for the inputs to AI agents: specs, system prompts, technical text and prompt tests. Each app is free to use, and one Utilities Pro plan ($5.99/month or $59.99/year) unlocks Pro in all four.

  • Dev Text Forge's workbench: an informal note about a deploy script in the source pane, next to the optimized output pane and quality gates

    Dev Text Forge

    Dev text optimizer

    You are here

    Rewrite developer text into clear technical English that keeps every token.

    Pro adds in Dev Text Forge

    • Agent context mode
    • Token diet report
    • Batch optimize
  • SpecStudio's Studio: a travel-booking request with allowed domains, constraints and success criteria, ready to compile into a spec

    SpecStudio

    Agent task specs

    Turn a rough request into a safety-gated spec a browser agent can follow.

    Pro adds in SpecStudio

    • Spec risk audit (OWASP LLM Top 10)
    • Export to AGENTS.md, CLAUDE.md and Cursor rules
    • Live page grounding
    • Pro template pack
    Open SpecStudio
  • Prompt Guardian's refinement dashboard: a support-agent system prompt in the editor with a clean static scan

    Prompt Guardian

    Gated prompt governance

    Attack, score and gate every system prompt change before it ships.

    Pro adds in Prompt Guardian

    • Advanced attack packs
    • OWASP LLM Top 10 (2025) report
    • Regression guard for CI
    Open Prompt Guardian
  • PromptForge's tool directory: prompt-engineering tools such as System Prompt Maker, Prompt Optimizer and Image to Prompt

    PromptForge

    Prompt engineering toolbox

    A prompt-engineering toolbox: generators, a linter, tests and a workspace.

    Pro adds in PromptForge

    • Prompt linter
    • One-click prompt hardening
    • Assertion-based prompt tests
    Open PromptForge

Free to start. One price for Pro everywhere.

Use Dev Text Forge free for as long as you like. When you want the Pro features, one plan covers all four utilities.

Prices in USD, taxes included. One plan for all four apps.

Free

Everything Dev Text Forge does today. No card, no trial clock.

$0forever

Sign in with Google or email.

  • Prose and Structured prompt optimization modes
  • Fidelity, rules, structure, length and schema gates
  • Documents with full version history
  • Model bake-off, prompt contracts and custom gates
  • Regression timeline and agent profile
Start free
Recommended

Utilities Pro Pro

Pro features in Dev Text Forge and in the other three utilities.

$5.00per month

Billed $59.99 once a year. Save 17% versus monthly.

7-day Pro trial, no card required

Sign in with Google and it starts by itself: every Pro feature in all four apps, with up to 30 Pro actions a day (100 in total) and 3 premium-model runs a day (5 in total). Then you're back on Free automatically; nothing to cancel.

One trial per email. Not available to emails that already had Utilities Pro, and new trials are limited each day.

  • Everything in Free
  • Agent context mode
  • Token diet report
  • Batch optimize
  • Premium models
  • Pro editor: AI assist, cloud history, HTML/PDF export, token budget

Pro in all four apps

  • Dev Text ForgeThis app
  • SpecStudioAgent task specs
  • Prompt GuardianGated prompt governance
  • PromptForgePrompt engineering toolbox
Free and Utilities Pro compared, app by app
FeatureFreePro
In Dev Text Forge
Prose and Structured prompt optimization modes
Fidelity, rules, structure, length and schema gates
Documents with full version history
Model bake-off, prompt contracts and custom gates
Regression timeline and agent profile
Agent context modeOptimize AGENTS.md, CLAUDE.md, .cursorrules and Copilot instructions: drop duplicate and conflicting rules, one imperative rule per line, commands and paths kept verbatim, with a report of every change.
Token diet reportEstimated tokens before and after each optimization, the reduction, and the tokens saved per 1,000 agent runs.
Batch optimizeOptimize up to 10 files or saved documents in one run, with progress, per-file gate results, retries and a .zip or combined Markdown download.
Premium modelsThe large models in every model picker: Claude Opus 5.5, Claude Sonnet 5.5, Mistral Large 4 and Mistral Medium 3.5. Claude Haiku 5.5 (the default), Mistral Medium 3.1, Devstral 2, DeepSeek and the other fast models stay free for everyone.
Pro editor (every app)
AI writing assist in the editorRewrite, tighten, fix, expand or turn any selection into a checklist.
Cloud version historyEvery save kept in the cloud, with a side-by-side diff and one-click restore.
HTML and PDF exportShare polished documents with stakeholders who never open a Markdown file.
Token and context budgetSee how much of each model's context window a document uses before you paste it.
In SpecStudio
SpecStudio: everything free todayTurn a rough request into a safety-gated spec a browser agent can follow.
Spec risk audit (OWASP LLM Top 10)
Export to AGENTS.md, CLAUDE.md and Cursor rules
Live page grounding
Pro template pack
In Prompt Guardian
Prompt Guardian: everything free todayAttack, score and gate every system prompt change before it ships.
Advanced attack packs
OWASP LLM Top 10 (2025) report
Regression guard for CI
In PromptForge
PromptForge: everything free todayA prompt-engineering toolbox: generators, a linter, tests and a workspace.
Prompt linter
One-click prompt hardening
Assertion-based prompt tests
  • Free stays free. Pro only adds; nothing you use today moves behind the paywall.
  • Cancel anytime from Settings → Billing. Pro stays active until the end of the period you paid for.
  • One subscription, four apps. In another app, sign in with Google using the same email and Pro is already on.
  • Secure checkout by Dodo Payments, merchant of record. It handles sales tax and VAT; prices include them.

Questions, answered

How is this different from asking a chatbot to fix my English?

It is a single-purpose pipeline with deterministic checks. A chatbot will not tell you that it dropped a flag or changed a number; the fidelity gate does, with the line.

Is the free plan really free?

Yes. Both optimization modes, all the quality gates, documents with history, the bake-off, contracts and custom gates are free with no card and no trial period.

What does Utilities Pro add here?

Agent context mode for AGENTS.md and similar files, the token diet report, batch optimize, the Pro editor tools, and the premium models: Claude Opus 5.5, Claude Sonnet 5.5, Mistral Large 4 and Mistral Medium 3.5. The same plan unlocks Pro in the other three utilities.

Will it change my code?

No. Code spans and fenced blocks are preserved, and the fidelity gate flags any that differ between input and output.

Which models does it use?

Claude Haiku 5.5 by default, with Mistral Medium 3.1 via OpenRouter as the fallback; other models are in the model picker and the bake-off. Free: Claude Haiku 5.5, Mistral Medium 3.1 and Devstral 2 (processed in the EU), plus DeepSeek, Xiaomi MiMo and Zhipu GLM, which run only when you pick them and are processed in China. Claude Sonnet 5.5, Claude Opus 5.5, Mistral Large 4 and Mistral Medium 3.5 come with Utilities Pro. Optional web search can check current facts.

Can I cancel Utilities Pro?

Anytime, from Settings → Billing. You keep Pro until the end of the period you paid for, then the free plan continues.

Your next PR description can read like a native wrote it.

Start free with every gate. Upgrade for agent context mode and batch optimize, in this app and the other three.

Rewrite a text free