Anthropic's Claude Code mods, on by default from 2.1.287, let JavaScript or TypeScript code rewrite prompts, block tool calls and approve permission requests. For teams, the governance question moves from what the agent is told to which code it runs.
Perspective Coverage
5 publishers
- Builder
- Builder 59%
- Operator
- Operator 36%
- Investor
- Investor 5%
Reality
- Evidence78
- Adoption15
- Hype gap+15
- Incentives60
- Confidence72
Cloudflare's cloudflared 2026.9.3 adds an --allowed-mail flag that limits a Quick Tunnel to approved email addresses via a one-time PIN. Public stays the default, so the safeguard works only if whoever starts the tunnel, increasingly a coding agent, adds the flag.
Reality
- Evidence45
- Adoption
- Insufficient
- Hype gap+10
- Incentives65
- Confidence45
Relipa's AI development workflow wraps a coding agent in six stages and fixes the tests before any code is written. Most of its published detail covers the workspace plumbing that runs before a model is ever called.
Reality
- Evidence35
- Adoption8
- Hype gap+5
- Incentives
- Insufficient
- Confidence40
AI code reviewers lose hosted rule ingestion first on self-managed GitLab, Azure DevOps Server and Bitbucket Data Center, a dev.to comparison says. Of the three mechanisms it compares, only a pass/fail rule can block a merge, and vendors tend to put that one on paid tiers.
Reality
- Evidence40
- Adoption
- Insufficient
- Hype gap+20
- Incentives
- Insufficient
- Confidence40
Eval harness agents-md-evals found 25 of 26 assertions passed identically with or without a 755-line AGENTS.md file. The finding rests on that one file, and it assumes the agent loaded the file in the first place.
Reality
- Evidence30
- Adoption
- Insufficient
- Hype gap+40
- Incentives
- Insufficient
- Confidence35
The model documentation concedes Astra asks for clarification more often than GPT-5.6 Sol and sometimes stops early. Every remedy on the page is more instruction text, loaded into the same context the docs blame for stalls.
Reality
- Evidence62
- Adoption
- Insufficient
- Hype gap+10
- Incentives50
- Confidence65
A dev.to post credits Anthropic with running the same model and the same prompt under two harnesses, 20 minutes and $9 for a broken result against six hours and $200 for a working one. The hourly spend barely moved.
Reality
- Evidence25
- Adoption
- Insufficient
- Hype gap+30
- Incentives45
- Confidence40
Claude Code started reading AGENTS.md on September 18, but only where no CLAUDE.md sits in the working directory or any parent above it. Monorepos need a stub file per package or a change to the instructionFiles setting.
Reality
- Evidence55
- Adoption40
- Hype gap+10
- Incentives35
- Confidence55
Version 2.1.277 reads a shared AGENTS.md when no CLAUDE.md is in scope. The documented exceptions cover first sessions, telemetry-disabled runs, Bedrock, Vertex and Foundry, and the hooks governance tooling watches.
Reality
- Evidence68
- Adoption58
- Hype gap+12
- Incentives62
- Confidence64
A dev.to template for CLAUDE.md and AGENTS.md swaps style adjectives for Avoid/Preferred code pairs that name the exact helper an agent should call, on the argument that a code shape is the only part a model can imitate.
Reality
- Evidence34
- Adoption
- Insufficient
- Hype gap+22
- Incentives20
- Confidence50
Anthropic shipped the AGENTS.md fallback in Claude Code 2.1.277 as a flag-gated built-in mod. Two machines on the same pinned version can load different project instructions. The same week's digest also logs a reverted deny-rule fix.
Perspective Coverage
4 publishers
- Builder
- Builder 52%
- Operator
- Operator 39%
- Investor
- Investor 9%
Reality
- Evidence78
- Adoption62
- Hype gap−6
- Incentives58
- Confidence74
Anthropic's memory documentation sets a 200-line target per instruction file and reserves real blocking for a hook. Everything written in markdown arrives as context the model weighs against your last message.
Publishers:code.claude.com
Reality
- Evidence68
- Adoption
- Insufficient
- Hype gap+12
- Incentives60
- Confidence62
shinpr has taken claude-code-workflows through 133 releases, and the recent ones delete structure the models no longer need. His session reader then found three mandatory steps in his own repository that never ran.
Reality
- Evidence42
- Adoption18
- Hype gap+12
- Incentives58
- Confidence46
Claude can now read AGENTS.md, the file other agent tools already look for. XDA-Developers reports developers called the change small and long overdue, and the Claude-specific syntax that forced a second file has not moved.
Reality
- Evidence42
- Adoption28
- Hype gap+45
- Incentives55
- Confidence45
Derek Wang's essay argues agent reliability is set by a file the model reads before any task prompt. Its ten behavior rules split into the ones a harness can verify and one the model grades itself on.
Reality
- Evidence30
- Adoption
- Insufficient
- Hype gap+30
- Incentives45
- Confidence60
Claude Code now supports AGENTS.md through a built-in plugin with four loading modes. The default treats the two filenames as alternatives, and the mode itself is set in user or managed settings outside the repo.
Reality
- Evidence72
- Adoption45
- Hype gap−10
- Incentives58
- Confidence66
The opencode-agent-memory plugin gives an OpenCode agent scoped Markdown blocks it rewrites through three tools, plus an opt-in journal it can search locally but never revise. The maintainer documents the failure modes himself.
Reality
- Evidence34
- Adoption14
- Hype gap−12
- Incentives38
- Confidence52
A month and a half of prototyping an experimental functional language with Codex ended with eight artifacts around the repository and a documentation flow in which ChatGPT writes the prompts and Codex writes the spec.
Reality
- Evidence26
- Adoption12
- Hype gap+22
- Incentives30
- Confidence52
Prose in AGENTS.md did not stop it, so the project now enumerates agent skills from disk and runs a script that exits non-zero on any copy outside the canonical root, including an empty leftover directory.
Reality
- Evidence42
- Adoption12
- Hype gap+12
- Incentives30
- Confidence46
GoVueKit puts a table of its subsystems in AGENTS.md and holds it with a Go test that fails when a package goes unmapped or a listed path disappears. That covers existence and names, not the descriptions.
Reality
- Evidence42
- Adoption
- Insufficient
- Hype gap+25
- Incentives85
- Confidence48
Earlier coverage
- Claude Code picks up Monday from the correction card Codex wrote on Saturday
Build · September 14, 2026 · 1 publisher
- A page behind Chrome's WebMCP flag registers three agent tools without an MCP server
Build · September 14, 2026 · 1 publisher
- The classifier that put gotchas in 13.6% of AGENTS.md files catches barely a third of them
Build · September 14, 2026 · 1 publisher
- A label on a GitHub issue now fires the event setup that took a couple of days by hand
Build · September 11, 2026 · 1 publisher
- Cursor's plugin.json puts agent tool scope where a code reviewer can diff it
Build · September 11, 2026 · 1 publisher
- Tool logs caught six frontier models ignoring an instruction they said they followed
Build · September 10, 2026 · 1 publisher
- A six-hour agent run harvested credentials from behind the victim's own cloud IPs
Build · September 10, 2026 · 1 publisher
- Red Hat tells its engineers to take the keyboard back when prompting costs more than typing
Product · September 7, 2026 · 1 publisher
- A six-assertion test blocks any commit that grows CLAUDE.md past 45,000 bytes
Build · September 4, 2026 · 1 publisher
- Claude Code's creator now advises deleting your CLAUDE.md every six months
Product · August 31, 2026 · 1 publisher
- Undocumented rejections come back as confident agent proposals three weeks later
Build · August 29, 2026 · 1 publisher
- Four zero bytes at byte 14 walk FFmpeg's VPK demuxer into a division by zero
Build · August 28, 2026 · 1 publisher
- Mozilla's fake Python tool talked a coding agent into opening a reverse shell
Product · August 27, 2026 · 1 publisher
- Block says 95% of its engineers use AI daily. The interesting part is who runs five agents.
Leadership · August 26, 2026 · 1 publisher
- Codex remembers by popularity: who actually decides what your agents forget
Build · August 26, 2026 · 1 publisher
- Twenty-three security checks, zero coverage: AI coding agents as build-pipeline attack surface
Build · August 25, 2026 · 1 publisher
- Copilot code review only ever files comments, so stop buying it as a merge gate
Build · August 25, 2026 · 1 publisher
- Ambient Context turns the focused macOS window into a Markdown day file, no screenshots
Build · August 25, 2026 · 1 publisher
- OpenCode has no memory subsystem. It has three mechanisms that fail differently
Build · August 25, 2026 · 1 publisher
- Test the rule change, not the model: a cheap A/B harness for agent standards
Build · August 23, 2026 · 1 publisher
- The compiler checks three of the seven things your coding agent had to get right
Build · August 23, 2026 · 1 publisher
- The personal agent is a folder, not a model: four files and less memory than you thought
Product · August 22, 2026 · 1 publisher
- Agent protocols now share one landlord: A2A joins MCP and AGENTS.md at the Linux Foundation
Product · August 20, 2026 · 1 publisher
- NVIDIA is documenting Holoscan for the agent, not the engineer
Build · August 20, 2026 · 1 publisher
- The AGENTS.md file is an audit of the documentation you never wrote for humans
Build · August 19, 2026 · 1 publisher
- OpenAI writes down the AGENTS.md merge order, and agent config becomes auditable
Build · August 19, 2026 · 1 publisher
- A 2x LLM bill is not a bug report: token spend is an observability problem
Product · August 18, 2026 · 1 publisher
- The linter that passed everyone who ignored it and warned everyone who complied
Build · August 17, 2026 · 1 publisher
- The Context Tax: Your Developers Are Doing Unpaid Platform Work Every Session
Build · August 15, 2026 · 1 publisher
- A "Done." is a claim about the world, not a sentence you can grade
Build · August 15, 2026 · 1 publisher
- The payload is rebuilt every turn, so stop treating your prompt as a shipped artifact
Build · August 15, 2026 · 1 publisher
- A coding agent deleted the rule its own rename had broken
Build · August 14, 2026 · 1 publisher