overcast-timeline

overcast-timeline is a skill for Claude Code, Codex from kdr/overcast. It costs 36 tokens per session (683 once invoked), scanned A, original, Apache-2.0.

A video-analysis workflow for rebuilding one event's timeline from several recordings. It aligns shared moments across clips and records agreement or disagreement with citations.

In plain words
What is it for?
Use it to analyze bystander videos and camera footage, align clips using clocks or shared sounds, document corroborating evidence, and flag genuine contradictions.
Why use it?
It helps create one reliable sequence from overlapping camera or phone footage instead of reviewing each recording in isolation.

Skill for Claude CodeCodex

Part of the overcast plugin — 35 skills, 1 hook shipped together

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

Made for: Claude Code, Codex.

Or install overcast, the plugin that ships this one along with the rest of its 35 skills, 1 hook.

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 overcast-timeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/kdr/overcast/overcast-timeline.svg)](https://agentmods.dev/skills/kdr/overcast/overcast-timeline)
Your own site
<a href="https://agentmods.dev/skills/kdr/overcast/overcast-timeline"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-timeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 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 $0.00036 $0.00683
Opus 5 $0.00018 $0.00342
Sonnet 5 $0.00007 $0.00137
Haiku 4.5 $0.00004 $0.00068

Measured 5d ago against content hash e934aa8d3157, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

overcast-timeline 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 5d 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/overcast-timeline/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

overcast-timeline

Use this skill to "walk through what happened" across several recordings of one event (bystander videos, multiple cameras, a sequence of clips): build one ordered, cited timeline and flag where accounts disagree. Use the broad overcast skill and overcast/reference/verbs.md for exact flags.

Workflow

  1. Sense every clip — watch for the visual timeline, listen where audio carries the account:
overcast doctor --json
overcast case init --json
overcast watch ./cam1.mp4 --json
overcast watch ./phone-clip.mp4 --json
overcast listen ./phone-clip.mp4 --json
  1. Cross-anchor shared moments with span notes — a visible clock, a shared sound, a lighting change lets you line clips up on one timeline:
overcast note "wall clock reads 21:14 as the door opens" --ref <cam1-record-id> --at 12-15 --tag anchor --json
overcast note "same doorbell chime as cam1@13 — clips overlap here" --ref <phone-record-id> --at 3-6 --tag anchor --json
  1. Corroborate and contradict across clips. File a conflict finding ONLY when the answer actually reports a disagreement — don't invent one every run; if the accounts agree, record that and skip the finding:
overcast ask "order the events across all clips with timestamps; where do accounts agree or conflict? cite record.id + media.at" --json
# only if the answer reports a real conflict:
overcast finding create "conflict: cam1 shows the car arriving BEFORE the shout; phone-clip audio has the shout first" --ref <cam1-record-id> --at 12-15 --confidence low --json
  1. Produce the chronological deliverable, and always leave a tldr note first:
overcast note "reconstructed <n> clips into one timeline; <k> firm anchors; <c> unresolved conflicts" --tag tldr --json
# Wait for the note result before exporting, so the TL;DR is included.
overcast brief --export ./timeline.html --json

Output

One ordered chronology of the event, each entry cited to a record.id + media.at, the anchor moments that let clips be aligned, and an explicit list of unresolved contradictions. Where clips can't be ordered relative to each other, say so rather than guessing.

Read the full file on GitHub · 69 lines

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. 5d ago First seen · 69 lines · 36 tokens per session scan A e934aa8d3157

Subscribe to this mod's changes

overcast-timeline is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 683 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 2026-08-30.

Related

Other skills, from other repositories

video-to-skill

Turn a video, tutorial, playlist, or course into an installed, evidence-grounded course Skill that can teach, give practice and feedback, apply demonstrated methods, and answer reference questions. Use when the user provides video sources and wants reusable learning or operational capability.

Lum1104/video-to-skill · 57 tokens

frame-light-leak-cinema

Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.

nexu-io/open-design · 31 tokens

osmedeus-expert

Expert guide for the Osmedeus security automation workflow engine. Use when: (1) writing or editing YAML workflows (modules and flows), (2) running osmedeus CLI commands (scan, workflow management, installation, server), (3) configuring steps, runners, triggers, or template variables, (4) debugging workflow execution…

j3ssie/osmedeus · 113 tokens

recon-tool-integration

Adding a new tool to the recon pipeline: the enrichment-module contract and its isolated wrapper (the actual fan-out and test call path), graph completeness, and the preset catalog that silently strips unknown settings. Miss the isolated wrapper and the tool never runs in parallel; miss the catalog and AI presets drop…

samugit83/redamon · 114 tokens

supply-chain-scan

Working on RedAmon's supply-chain scanner (offline OSV + GuardDog + retire + trufflehog): the offline OSV database that the scan path does not bootstrap, the world-readable requirement for the hardened scanner, and the soft-error markers that record what was never analysed. Trigger: editing…

samugit83/redamon · 115 tokens

frame-glitch-title

数字故障 / 像散偏移 / 数据腐败标题, 适合视频转场 / cyberpunk hero.

nexu-io/html-anything · 31 tokens