A shared, append-only work log for recording an agent team's milestones. Entries can capture results, decisions, blockers, and handoffs, and can be searched by time, project, or entry.

Use it at the start of substantial shared work and at milestones to read recent activity or add a linked project update.

It helps agents see related recent work before starting and leaves a concise record for teammates. This reduces duplicated effort and makes handoffs easier to follow.

How marin-community/marin configures Claude Code and Codex

About the project

Marin is an open-source research program, software platform, and community for developing foundation models such as large language models. Researchers use it for data preparation, tokenization, pretraining, posttraining, evaluation, and related experiments, including work on audio-text, DNA, and protein models. The catalogue entries are add-ons that support workflows around Marin.

marin-community/marin · 4,074 stars · on GitHub · marin.community

Reuse

Borrowing it

Nothing to install: this file belongs to marin-community/marin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/marin-community/marin/main/.agents/skills/echo-log/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/marin-community/marin

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marin-community/marin/echo-log/github.svg)](https://agentmods.dev/skills/marin-community/marin/echo-log)

Your own site

<a href="https://agentmods.dev/skills/marin-community/marin/echo-log"><img src="https://agentmods.dev/badge/skills/marin-community/marin/echo-log/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marin-community/marin/echo-log"><img src="https://agentmods.dev/badge/skills/marin-community/marin/echo-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 555 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00052	$0.00555
Opus 5.5	$0.00021	$0.00222
Sonnet 5.5	$0.00010	$0.00111
Haiku 4.5	$0.00005	$0.00056

Measured yesterday against content hash d578a9c1ea92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

echo-log 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 yesterday.

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/skills/echo-log/SKILL.md · 56 lines

What it actually says

Echo work log

The work log is Echo's append-only team logbook. Each entry records one milestone of an agent's work: a result, a decision, a blocker, or a handoff. The Echo dashboard shows recent entries at /echo/conversation.

Read

At the start of non-trivial shared work, check whether another agent already works on it:

uv run infra/marina/apps/echo/cli.py work-log recent --days 7
uv run infra/marina/apps/echo/cli.py work-log projects --days 30
uv run infra/marina/apps/echo/cli.py work-log recent --project <slug>
uv run infra/marina/apps/echo/cli.py work-log show <id>

recent prints one summary line per entry, newest first. projects prints each project slug with its entry count, most recently active first. show prints one entry with its body.

Write

Add one entry at each milestone:

uv run infra/marina/apps/echo/cli.py work-log add --project <slug> --title "<result or decision>" --body - <<'EOF'
<two or three sentences with links to the PR, issue, run, or report>
EOF

Use one stable --project slug for each thread of work, across sessions and agents, for example harbor:issue-161. Run projects to find an existing slug before you make a new one. Echo stores slugs in lowercase.
Write the title as the result or decision. Keep the body short and link the evidence. Do not paste transcripts, raw logs, or secrets.
Echo records the signed-in caller as the author.

Access

The CLI uses the shared Marin IAP login (iris login) or ambient service-account credentials. See Echo setup and access.

If the caller has no credentials or no IAP access, recent, projects, and show exit 1 with the error, and add prints Work-log entry not written and exits 0. After the first such refusal, do not use the work log again in this session. Do not retry, change credentials, or debug access for the work log. Continue the task without it.

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.

yesterday First seen · 56 lines · 52 tokens per session scan A d578a9c1ea92

Subscribe to this mod's changes

echo-log is a skill published in the GitHub repository marin-community/marin (4,074 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 555 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-05.

Productivity Project management

echo-log next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
echo-logmarin-community/marin	Skill	4.1k	today	Apache-2.0	A	52	Claude Code, Codex
orbit-notionnexu-io/open-design	Skill	106k	today	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	today	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex

marin: Skill for Claude Code