What is project-with-reflect AGENTS.md?

Repository instructions for a project that teaches coding agents to keep persistent project notes and improve from past work. It uses generated instruction files, dashboards, decisions, and lessons stored in a local folder.

Use it when working on projects or connections managed by project-with-reflect: load the relevant notes, record durable findings, and close sessions with a reflection.

It gives the agent a record of earlier decisions and lessons, reducing repeated mistakes and keeping project knowledge between sessions.

project-with-reflect AGENTS.md — Instructions file by initialneil

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/initialneil/project-with-reflect/agents-md

Clone the repo

git clone --depth 1 https://github.com/initialneil/project-with-reflect

Made for: Codex, OpenCode.

Per session 420 This file is loaded in full into every session.

When invoked 420 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.

Model	Per session	Once invoked
Fable 5	$0.00420	$0.00420
Opus 5	$0.00210	$0.00210
Sonnet 5	$0.00084	$0.00084
Haiku 4.5	$0.00042	$0.00042

Measured 2d ago against content hash 1fa969d90fae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-with-reflect 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 · 32 lines

What it actually says

project-with-reflect Agent Instructions

This repository publishes the project-with-reflect skill for multiple coding agents.

Use the canonical skill at skills/project-with-reflect/SKILL.md for behavior. It registers projects and connections as persistent, self-improving skills backed by a local $PROJECT_WITH_REFLECT_ROOT, usually an Obsidian vault folder such as Project-with-Reflect.

Before acting on a project or connection managed by this skill:

Load the relevant generated SKILL.md, dashboard note, decisions.md, and matching lessons.
Check prior decisions before proposing new direction.
Record durable findings with record and close sessions with reflect.
Keep secrets out of disk state; store only env-var names or ssh aliases.
If running in Codex, Claude Code, or Kimi Code, use the user-scope skill install in ~/.codex/skills/project-with-reflect, ~/.claude/skills/project-with-reflect, or ~/.agents/skills/project-with-reflect respectively.

Agent-specific entrypoints in this repo are lightweight adapters:

.codex/skills/project-with-reflect/ for Codex.
.claude/skills/project-with-reflect and .claude-plugin/ for Claude Code.
.kimi-code/skills/project-with-reflect/ and ~/.agents/skills/project-with-reflect for Kimi Code. The same adapter is mirrored into Kimi Work (kimi-desktop) at daimon-share/daimon/skills/project-with-reflect; generated skills follow via doctor.
.cursor/rules/project-with-reflect.mdc for Cursor.
.gemini/GEMINI.md for Gemini CLI.
.opencode/AGENTS.md for OpenCode.
.continue/prompts/project-with-reflect.md for Continue.
.github/copilot-instructions.md for GitHub Copilot coding agent.

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.

2d ago First seen · 32 lines · 420 tokens per session scan A 1fa969d90fae

Subscribe to this mod's changes

project-with-reflect AGENTS.md is an instructions file published in the GitHub repository initialneil/project-with-reflect (13 stars, last pushed 14d ago), licensed MIT. It adds 420 tokens to every session, about $0.0021 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 2026-08-30.

Analytics and metrics Learning and teaching Productivity

project-with-reflect AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

project-with-reflect Agent Instructions

What this file has done since we first saw it

Other instructions, from other repositories

python-cheatsheet copilot-instructions.md

Tutorial_AwesomeModernCPP AGENTS.md

fix-quera AGENTS.md

ab900 CLAUDE.md

agentconfig.org AGENTS.md

canvas-lms-mcp AGENTS.md