03-journal-format

A set of journal and coordination rules for teams of coding agents. Each agent records its current work, blockers, approvals, and next steps in a shared status file.

In plain words
What is it for?
Use it to maintain agent status journals, record approvals and proposals, and document task or launch actions during a multi-agent project.
Why use it?
It keeps important project state visible and reduces confusion when agents work in parallel. It also gives the team a consistent place to find updates instead of relying on private messages.

Cursor rule for Cursor

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 rules/anshulixyz/multi-agent-loop-kit/03-journal-format
Clone the repo
git clone --depth 1 https://github.com/anshulixyz/multi-agent-loop-kit

Made for: Cursor.

Per session 188 This file is loaded in full into every session.
When invoked 188 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.

ModelPer sessionOnce invoked
Fable 5 $0.00188 $0.00188
Opus 5 $0.00094 $0.00094
Sonnet 5 $0.00038 $0.00038
Haiku 4.5 $0.00019 $0.00019

Measured 3d ago against content hash 555bf246b4a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

03-journal-format 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 3d 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.

.cursor/rules/03-journal-format.mdc · 46 lines

What it actually says

Journal rules

Each agent maintains:

agents-status/<codename>.md

Update it:

  • at session start
  • before stopping
  • when blocked
  • after shipping
  • after creating approval/proposal
  • after accepting/skipping Beacon task

Use exactly this schema:

## Now
## Just shipped
## Blocked / waiting on
## Discussion needed
## Approvals open
## Proposals open
## Next
## Notes

Write nothing in empty sections.

Never coordinate meaningful build state through private chat. Put it in journals, approvals, proposals, or task briefs.

Use these prefixes:

[task] <agent>: <action>
[approval] operator: <approval path>
[setup] operator: <setup action>
[launch] operator: <demo/launch action>
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. 3d ago First seen · 46 lines · 188 tokens per session scan A 555bf246b4a2

Subscribe to this mod's changes

03-journal-format is a cursor rule published in the GitHub repository anshulixyz/multi-agent-loop-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 188 tokens to every session, about $0.0009 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 2026-08-31.