register-project

A command that adds a project to project-with-reflect, a system for keeping project details and work history. It reads a plain-language project description and creates the project record.

In plain words
What is it for?
Use it to register a new code project, including its location, remote server, extra repositories, worktree setup, and whether existing documentation should be imported.
Why use it?
It removes the need to know and type setup flags for local, remote, or multi-repository projects. It also asks only about details that are missing or unclear.

Command

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 commands/initialneil/project-with-reflect/register-project
Clone the repo
git clone --depth 1 https://github.com/initialneil/project-with-reflect
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 389 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 $0.00014 $0.00389
Opus 5 $0.00007 $0.00195
Sonnet 5 $0.00003 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 2d ago against content hash 6d852a86966e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

register-project 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.

commands/register-project.md · 23 lines

What it actually says

Run the register-project action of the project-with-reflect skill with arguments: $ARGUMENTS

The user describes the project in plain language — you translate it into the script's flags. They should never have to type --remote / --root / :role themselves. From $ARGUMENTS extract: the project name, its path(s), whether the code is local or remote (cues like "on the gpubox server", "it's on <host>", a user@host:/path), and any extra repos it spans ("also uses the dataset repo at …"). Only AskUserQuestion for what's genuinely missing or ambiguous — workstream_mode (worktree|in-repo|logical), whether to import existing docs. (Project state always lives centrally — project-with-reflect is personal memory; there is no in-repo state mode.)

Then read the skill's SKILL.md and run its register-project steps:

  • If the project is remote and its host isn't a registered connection yet, register it first (register-machine <host> — point the user at a key-based Host block in ~/.ssh/config).
  • Run scripts/register-project.sh <name> <primary-path> [workstream_mode], adding --remote <connection> for a remote project and a repeatable --root <path>[:role] per extra root. These flags are the deterministic interface you fill in from the description — not user-facing.

Report the new /<name> command, and offer /<name> bootstrap to seed it from existing docs.

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. 2d ago First seen · 23 lines · 14 tokens per session scan A 6d852a86966e

Subscribe to this mod's changes

register-project is a command published in the GitHub repository initialneil/project-with-reflect (13 stars, last pushed 14d ago), licensed MIT. It adds 14 tokens to every session and 389 once invoked, about $0.0001 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.