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.
npx skills add kdr/overcast --skill overcast-pinpointgit clone --depth 1 https://github.com/kdr/overcastWrote 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.
[](https://agentmods.dev/skills/kdr/overcast/overcast-pinpoint)<a href="https://agentmods.dev/skills/kdr/overcast/overcast-pinpoint"><img src="https://agentmods.dev/badge/skills/kdr/overcast/overcast-pinpoint.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.00847 |
| Opus 5 | $0.00018 | $0.00424 |
| Sonnet 5 | $0.00007 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
overcast-pinpoint 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
overcast-pinpoint
Use this skill to answer "exactly when does X happen?" in a clip and back it
with evidence the model actually looked at. It mirrors the temporal-search
pattern from the VLM video literature (T* / VideoAgent): score cheaply over the
whole clip, then spend expensive VLM calls only on a few candidate frames and
zoom in. Use the broad overcast skill and overcast/reference/verbs.md for
exact flags.
Two rules that make the answer trustworthy:
- Report a window, not a frame. Frame-exact localization is unreliable; emit
[t1-t2]plus one verified keyframe. - Every timestamp must trace to a frame you
see-verified. Never emit a time the model merely guessed — models answer correctly while grounding on the wrong moment, so confirm by looking at the frame.
Workflow
- Make the clip local and get a record id (
see frame://needs media on disk — capture a remote clip first).watchalso gives per-shot timestamped content to search:
overcast doctor --json
overcast case init --json
overcast watch ./clip.mp4 --json # -> video.analysis record id (REC)
- Get COARSE candidates cheaply (pick what's available):
overcast ask "moments where <X> happens, with timestamps" --json # over watch shots/notes
overcast grid ./clip.mp4 --count 16 --json # one contact sheet ...
overcast see <montage-path> --prompt "which numbered cells show <X>? give cell numbers" --json
overcast similar search "<X>" --index <basic-clip-id> --json # if a local CLIP index exists
overcast ask "moments <X> happens" --index <media-descriptions-id> --probe --json # remote index
For grid, translate the chosen cell number to a time via the grid record's
payload.cells[n].at (don't trust a model-guessed time). CLIP/shots only
SHORTLIST — CLIP is weak on actions/order — so verify next.
- VERIFY + zoom on each candidate time T (expensive, precise):
overcast see frame://REC@T --prompt "Is <X> happening here? answer yes/no and what you see" --json
# refine: sample T-d and T+d, halve d each round until adjacent frames flip yes<->no
overcast see frame://REC@<T-2> --prompt "Is <X> happening?" --json
overcast see frame://REC@<T+2> --prompt "Is <X> happening?" --json
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.
- 7d ago First seen · 80 lines · 37 tokens per session scan A a39c799e0a6c
overcast-pinpoint is a skill published in the GitHub repository kdr/overcast (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 847 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.
Other skills, from other repositories
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
frame-flowchart-sticky
SVG curve connectors, sticky-note nodes, and cursor interaction with a whiteboard-brainstorm feel.
frame-glitch-title
Digital glitch, chromatic offset, and data-corruption title frame for video transitions or cyberpunk heroes.
frame-logo-outro
Segmented logo assembly, glow bloom, and tagline reveal for video outros or brand closing frames.
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.