agentmods.dev

post-walk

post-walk is a skill for Claude Code from ohong/agent-skills. It costs 38 tokens per session (977 once invoked), scanned A, original, MIT.

A workflow for turning an Apple Voice Memo from a walk or commute into a transcript, notes, tasks, todos, and drafts.

In plain words
What is it for?
Use it when explicitly asked to process a walk or commute memo, including selecting the recording and transcribing it.
Why use it?
It converts spoken ideas into organized written material without requiring you to process the recording manually.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the post-walk plugin — 1 skill shipped together

not rated 3repo +1 8d ago A scan 38 tokens original MIT

Good fit Use it when explicitly asked to process a walk or commute memo, including selecting the recording and transcribing it.

Compare 6 skills from other repositories ↓
View source ↗ ohong/agent-skills
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ohong/agent-skills
Claude Code
/plugin install post-walk

Made for: Claude Code.

Or install post-walk, the plugin that ships this one along with the rest of its 1 skill.

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 post-walk

README.md
[![agentmods](https://agentmods.dev/badge/skills/ohong/agent-skills/post-walk/github.svg)](https://agentmods.dev/skills/ohong/agent-skills/post-walk)
Your own site
<a href="https://agentmods.dev/skills/ohong/agent-skills/post-walk"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/post-walk/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.

agentmods 80×15 button for post-walk

Your own site · 80×15
<a href="https://agentmods.dev/skills/ohong/agent-skills/post-walk"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/post-walk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 977 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 $0.00038 $0.00977
Opus 5 $0.00019 $0.00489
Sonnet 5 $0.00008 $0.00195
Haiku 4.5 $0.00004 $0.00098

Measured 8d ago against content hash 87cf3002fb4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

post-walk 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/transcribe.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

post-walk/skills/post-walk/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post-Walk Memo Processor

Memo to final report with no pauses in between. Do not launch follow-on work unless explicitly asked.

Pick the memo

  • Argument is a file path → use it (expand ~, verify it exists).
  • Otherwise → newest *.m4a by mtime in ~/Library/Group Containers/group.com.apple.VoiceMemos.shared/Recordings/. A non-path argument is a hint for naming/context/prioritization only.
  • Note path, recording timestamp, and duration (mdls, stat, ffprobe, or afinfo). If older than ~12h, flag as possibly stale and proceed.

Transcribe

Run ${CLAUDE_PLUGIN_ROOT}/skills/post-walk/scripts/transcribe.sh <audio-file> [output.txt] (path relative to this skill directory outside Claude Code). It speeds the audio up with ffmpeg before uploading to fal.ai Wizper — Wizper bills per audio second, and ASR handles sped-up speech fine. Factor: --speed N flag > POST_WALK_SPEED env var > 2.5 default; --speed 1 uploads unmodified. Requires FAL_KEY (env, ./.env, ./.env.local, or ~/.zshenv/~/.zprofile/~/.zshrc) and ffmpeg. Prints only the transcript path on success; errors go to stderr. Don't paste raw API responses into the report unless explaining a failure.

Archive

One walk folder: docs/walks/YYYY-MM-DD-<short-slug>/ inside a git repo, else ~/walks/YYYY-MM-DD-<short-slug>/. Slug = strongest memo theme (or the user's hint); fall back to walk-notes.

  • transcript.raw.txt — raw helper output, unchanged.
  • transcript.md — cleaned transcript (fix obvious ASR errors, add paragraph breaks, preserve the speaker's words) plus a short summary and a Misc section.
  • docs/<n>-<slug>.md — one agent-context doc per substantial idea.
  • tasks.md, todos.md, drafts.md — per the buckets below.

Buckets

Read the whole transcript before partitioning. Every piece of content lands in exactly one bucket — nothing dropped, nothing invented.

  • Context docs: per substantial idea, broad and deep agent context — problem, background, goals, constraints, useful facts, approaches, open questions. Don't compress away nuance. Open each with: > AI-written doc derived from voice memo <date>, intended as context for agents.
  • Eng tasks (tasks.md): title, spec, acceptance criteria, context-doc links, and a readiness label — ready (agent can start unaided) or needs-input (ambiguous).
  • Todos: personal/non-code items → Things via mcp__things__add_todo; if unavailable or an add fails, list those items in todos.md.
  • Drafts (drafts.md): emails, tweets, messages, essays as clean sendable drafts, separated by destination/audience.
  • Misc: real but unclassifiable → transcript.md under Misc.

Read the full file on GitHub · 56 lines

Files

What ships with it

1 file 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. 8d ago First seen · 56 lines · 38 tokens per session scan A 87cf3002fb4f

Subscribe to this mod's changes

post-walk is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 977 once invoked, about $0.0002 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.

ProductivityWriting and docs
Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens