set

A command for creating or updating a long-term project goal, including checkable acceptance criteria and a ranked list of work items.

In plain words
What is it for?
Defining project goals, recording what counts as finished, and maintaining an ordered backlog of increments.
Why use it?
It keeps the project’s objective and next tasks in a shared, git-tracked file instead of scattered notes.

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/zebbern/agent-collab/set
Clone the repo
git clone --depth 1 https://github.com/zebbern/agent-collab
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 329 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 $0.00011 $0.00329
Opus 5 $0.00005 $0.00164
Sonnet 5 $0.00002 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured 2d ago against content hash ae1dd0bb1672, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

set 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.

plugins/goal/commands/set.md · 26 lines

What it actually says

Create or update a goal file for this project.

  1. Interview briefly if needed: the goal statement, acceptance criteria (mechanically checkable commands where possible, manual otherwise), a ranked backlog of increments (each [a-z0-9-]+ id, title, detail), and budget.perStepDelegations (default 2).
  2. Draft the goal JSON (schemaVersion 1) to a temp file.
  3. Run: node "${CLAUDE_PLUGIN_ROOT}/scripts/goal-companion.mjs" set --file <temp-path> The companion validates and writes .claude/goals/<slug>.json; if it refuses, fix exactly what it names and re-run — never bypass validation. Renaming a slug: set writes the new file and never deletes the old one — remove .claude/goals/<old-slug>.json yourself, or status/next will refuse listing both.
  4. Show the result of node "${CLAUDE_PLUGIN_ROOT}/scripts/goal-companion.mjs" status <slug>.
  5. Remind the user the goal file is git-tracked project content: commit it.

Trust note: check runs command criteria via the shell — the same trust level as npm scripts. Review goal files in untrusted repos before running.

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 · 26 lines · 11 tokens per session scan A ae1dd0bb1672

Subscribe to this mod's changes

set is a command published in the GitHub repository zebbern/agent-collab (32 stars, last pushed 17d ago), licensed Apache-2.0. It adds 11 tokens to every session and 329 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.