devlog

A session journal for coding work in a Git repository, recording context, notes, blockers, and handoffs.

In plain words
What is it for?
It checks the session status, reads earlier handoffs, opens a session, records progress, and prepares a handoff when the work ends.
Why use it?
It helps preserve what happened during a coding task so work can continue later without reconstructing the previous session.

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/amohamma8029/devlog/skill
Any agent
npx skills add amohamma8029/devlog --skill skill
Clone the repo
git clone --depth 1 https://github.com/amohamma8029/devlog

Made for: Claude Code, Codex.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,539 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 $0.00081 $0.01539
Opus 5 $0.00041 $0.00770
Sonnet 5 $0.00016 $0.00308
Haiku 4.5 $0.00008 $0.00154

Measured yesterday against content hash 51cd3d278994, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devlog 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.

internal/skill/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devlog Session Skill

When to use

Activate this skill at the start of any coding task in a repository that has devlog installed. Verify devlog is installed with devlog --version before activating. This skill requires a git repository — devlog stores session data under .devlog/ in the repo root. Devlog captures structured session journals — context, notes, blockers, and handoffs — so you and your human collaborators can pick up where the last session left off.

Session lifecycle

1. Start of work — pick up context

  • Run devlog status to check for an active session and see recent events, blockers, and todos.
  • If a handoff exists from a previous session, read the newest file under .devlog/handoffs/ for context. Reading is fine; never write to .devlog/ directly — the CLI is the only writer.
  • If devlog status reports no active session, open one:
    devlog open "<one-line description of the task>"
    
  • If a session is already active from a prior task, check devlog status — if it's for a different task, ask the human whether to close it and reopen or continue under the existing session. The agent never runs devlog close itself. devlog allows only one active session at a time, repo-wide — not per-branch.
  • Re-run devlog status to confirm the session is active and see its initial state.
  • Review the todo list for outstanding work from prior sessions:
    devlog todo list
    
  • To see past sessions and their status:
    devlog list
    
    Use devlog list --active to show only open sessions.

2. During work — log milestones, blockers, and todos

  • Run devlog status periodically to verify the session state — recent events, blockers, and todos all appear in one view. Use devlog status -n 0 to see all events or devlog status -n 20 to see more recent ones (default is 10).
  • Add notes at meaningful milestones (after completing a subtask, making a decision, or discovering something worth recording):
    devlog note -m "<what you did or decided>"
    
  • Log blockers immediately when you hit one — don't wait:
    devlog block -m "<what is blocking you and what you tried>"
    
  • Fix a typo in a note or blocker using its event number from devlog status. Event numbers are most-recent-first — [1] is the newest event, [2] is the one before it, etc. The numbering is the same regardless of the -n flag value:
    devlog edit 2 -m "<corrected text>"
    
  • Remove an erroneous note or blocker entry:
    devlog edit 2 --delete
    
  • Use todos for outstanding work that should or will be revisited later — bugs, follow-ups, deferred items, things noticed but not addressed now. Todos added during an active session are auto-attributed to that session and branch:
    devlog todo add -m "Bug: locale fallback returns empty string on unknown code"
    
  • Mark todos done as you complete them. Use the number from devlog todo list:
    devlog todo done 2
    
  • Reopen a todo if something needs revisiting:
    devlog todo reopen 1
    
  • Fix a typo in a todo's text (only open todos can be edited — reopen first if you need to fix a completed one):
    devlog todo edit 1 -m "<corrected text>"
    
  • Remove a wrongly-added todo:
    devlog todo delete 1
    
  • Before editing or deleting, run devlog todo list and confirm the todo text matches the number you're targeting — completed todos are numbered after open ones, so the list position may not match your mental model.
  • If you need stable identifiers across sessions (list numbers reset per todo list call), use devlog todo list --ids to see internal IDs.
  • Filter todos by branch or session: devlog todo list --branch feat/auth or devlog todo list --session <session-id>.

Read the full file on GitHub · 99 lines

Files

What ships with it

2 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. yesterday First seen · 99 lines · 81 tokens per session scan A 51cd3d278994

Subscribe to this mod's changes

devlog is a skill published in the GitHub repository amohamma8029/devlog (2 stars, last pushed 13d ago), licensed MIT. It adds 81 tokens to every session and 1,539 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens