agentmods.dev

c-lockin

c-lockin is a skill for Claude Code, Codex from daxaur/openpaw. It costs 20 tokens per session (596 once invoked), scanned A, original, MIT.

A focus-session tool that blocks chosen websites and apps, prepares the working environment, and records when the session starts and ends.

In plain words
What is it for?
Use it to start and end timed deep-work sessions from the command line, with optional choices about which sites or apps to block.
Why use it?
It removes common distractions during a planned work period, so you do not have to block them manually each time.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash /tmp/lockin-start.sh.

not rated 167repo +1 3mo ago A scan 20 tokens original MIT

Good fit Use it to start and end timed deep-work sessions from the command…

Compare 6 skills from other repositories ↓
View source ↗ daxaur/openpaw npmjs.com
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/daxaur/openpaw
agentmods
npx agentmods add skills/daxaur/openpaw/c-lockin

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 c-lockin

README.md
[![agentmods](https://agentmods.dev/badge/skills/daxaur/openpaw/c-lockin.svg)](https://agentmods.dev/skills/daxaur/openpaw/c-lockin)
Your own site
<a href="https://agentmods.dev/skills/daxaur/openpaw/c-lockin"><img src="https://agentmods.dev/badge/skills/daxaur/openpaw/c-lockin.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 596 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00596
Opus 5 $0.00010 $0.00298
Sonnet 5 $0.00004 $0.00119
Haiku 4.5 $0.00002 $0.00060

Measured 7d ago against content hash 9f7b9f92061d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

c-lockin 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 7d 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/c-lockin/SKILL.md · 67 lines

What it actually says

Behavior

You run lock-in sessions using generated shell scripts — fast, one command. Be FAST. Say one short line like "Locking you in for 90 min" then run TWO commands max. Don't narrate steps. Only speak again when done ("Locked in until HH:MM") or if something fails.

Starting a Session

When the user says "lock in", "focus", "deep work", etc:

  1. Read ~/.config/openpaw/lockin.json. If missing → suggest openpaw lockin setup
  2. Check ~/.config/openpaw/lockin-session.json — if endsAt is in the future, session is already active. Tell the user.
  3. If config has askEachTime sites or apps, ask the user briefly which to include this session
  4. Calculate endsAt = now + duration minutes (ISO 8601 format, e.g. 2026-03-03T16:30:00.000Z)
  5. Say ONE short line like "Locking you in for 90 min"
  6. Generate scripts + run:
openpaw lockin gen-scripts --ends "ENDS_AT_ISO8601" --extra-sites "site1,site2" --extra-apps "App1,App2"

Omit --extra-sites and --extra-apps if none were chosen from askEachTime.

Then immediately run:

bash /tmp/lockin-start.sh
  1. Say "Locked in until HH:MM"

That's it — TWO bash commands to start a session.

Ending a Session

When the user says "stop", "end session", "I'm done":

  1. Read ~/.config/openpaw/lockin-session.json to get session data
  2. Run:
bash /tmp/lockin-end.sh
  1. Read the output for git stats
  2. If obsidianLog is true in config: obsidian-cli append daily "## Lock In Session\n- Duration: X min\n- Commits: N\n..."
  3. Give a brief warm summary: duration, commits + messages, lines changed, encouraging note referencing SOUL.md personality

Reconfigure

openpaw lockin setup

Guidelines

  • Be FAST — one line to start, two commands, one line when done
  • Never explain or narrate each step — just do it
  • If something fails, mention it briefly and move on
  • Only start when the user explicitly asks
  • Reference SOUL.md for personality in summaries
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. 7d ago First seen · 67 lines · 20 tokens per session scan A 9f7b9f92061d

Subscribe to this mod's changes

c-lockin is a skill published in the GitHub repository daxaur/openpaw (167 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 596 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.

Claude CodeProductivityai-agentanthropicautomationclaudeclideep-workdistraction-blockingfocuslockinpomodoro
Related

Other skills, from other repositories

work-log-codex

A workflow for turning Codex and Claude Code session records into readable Markdown work logs. It can organize activity by project and date range, such as today, this week, or a custom period.

ValorVie/custom-skills · 67 tokens

shell-scripting

A guide to writing Bash shell scripts, which automate command-line tasks on Linux and similar systems. It covers variables, arrays, conditions, loops, functions, and safer script structure.

chaterm/terminal-skills · 13 tokens

ansible

A guide for using Ansible, a tool that automates commands and configuration across multiple computers. It covers hosts, reusable playbooks, modules, permissions, and check mode.

chaterm/terminal-skills · 9 tokens

cron-manager

Create, inspect, pause, and remove scheduled jobs using natural language descriptions.

profclaw/profclaw · 17 tokens

apple-reminders

Create and manage Apple Reminders on macOS using AppleScript - set due dates, priorities, and lists.

profclaw/profclaw · 25 tokens

bear-notes

Create and manage notes in Bear on macOS using the Bear x-callback-url scheme.

profclaw/profclaw · 21 tokens