agent-log

agent-log is a skill for Claude Code, Codex from denysdovhan/agents. It costs 95 tokens per session (2,074 once invoked), scanned A, original, MIT.

A shared log for recording important engineering decisions in a project’s .agents/log folder. It keeps the reasons behind feature choices and trade-offs alongside the code.

In plain words
What is it for?
Use it when starting or finishing a significant feature, documenting a design choice, or updating the project’s decision journal.
Why use it?
It preserves context that may not be clear from source code or commit history, so developers and agents can understand why a decision was made.

Skill for Claude CodeCodex

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 skills/denysdovhan/agents/agent-log
Any agent
npx skills add denysdovhan/agents --skill agent-log
Clone the repo
git clone --depth 1 https://github.com/denysdovhan/agents

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.

agentmods badge for agent-log

README.md
[![agentmods](https://agentmods.dev/badge/skills/denysdovhan/agents/agent-log.svg)](https://agentmods.dev/skills/denysdovhan/agents/agent-log)
Your own site
<a href="https://agentmods.dev/skills/denysdovhan/agents/agent-log"><img src="https://agentmods.dev/badge/skills/denysdovhan/agents/agent-log.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,074 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 $0.00095 $0.02074
Opus 5 $0.00048 $0.01037
Sonnet 5 $0.00019 $0.00415
Haiku 4.5 $0.00010 $0.00207

Measured 4d ago against content hash 64e91efba1bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 4d 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.

skills/agent-log/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Log

Maintain .agents/log/ — a version-controlled journal of product and engineering decisions, tradeoffs, and directions, co-owned by the developer and agents. Entries capture why — the reasoning that code and git history cannot recover.

Layout

  • .agents/log/index.md — index of all entries
  • .agents/log/YYYY-MM-DD-slug.md — one entry per feature or standalone decision

Initialize .agents/log/ only when the user explicitly asks — by invoking this skill or directly requesting an agent log. If .agents/log/ is absent otherwise, do not create it, even when a plan is approved. When initializing, create .agents/log/index.md with the table header from Index Format; create an entry only if the current task records a decision.

Entry Format

---
title: Human-readable decision or feature title
date: YYYY-MM-DD
status: wip | done
related_paths:
  - src/feature-area/
  - src/shared/specific-file.ts
---

# Human-readable decision or feature title

## Background

Context needed to understand the problem. Link related entries as
[title](YYYY-MM-DD-other-entry.md).

## Problem

What is being solved and why now.

## Questions & Answers

Clarifying questions asked and the user's answers. Open questions stay
here until resolved.

## Decision

The chosen design. Concrete: file paths, type signatures, data shapes.
Mark examples with ✅ (do) and ❌ (don't) — the canonical notation for all
entries. Use Mermaid diagrams only when they clarify the decision.

## Tradeoffs & Alternatives

Rejected options and why. This section prevents re-litigating decisions
later.

## Implementation Plan

Phases or steps, when the entry starts as a plan draft.

## Verification

How success is checked, as a checklist:

- [ ] Tests, behaviors, or measurable criteria
- [ ] Manual checks that need a human

## Implementation Notes

Dated notes appended during and after implementation: deviations from
the plan, discoveries, test outcomes.

Make the level-one heading the first content after frontmatter and match its text exactly to the frontmatter title. Use only one level-one heading. Omit sections that have no content. Keep entries short and decision-focused — do not document what the code or git history already states.

Read the full file on GitHub · 193 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 193 lines · 95 tokens per session scan A 64e91efba1bd

Subscribe to this mod's changes

agent-log is a skill published in the GitHub repository denysdovhan/agents (17 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 2,074 once invoked, about $0.0005 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.