Borrowing it
Nothing to install: this file belongs to whistlegraph/aesthetic-computer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/whistlegraph/aesthetic-computer/main/.claude/skills/oskiewar-cull/SKILL.mdgit clone --depth 1 https://github.com/whistlegraph/aesthetic-computerWrote 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/whistlegraph/aesthetic-computer/oskiewar-cull)<a href="https://agentmods.dev/skills/whistlegraph/aesthetic-computer/oskiewar-cull"><img src="https://agentmods.dev/badge/skills/whistlegraph/aesthetic-computer/oskiewar-cull/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.
<a href="https://agentmods.dev/skills/whistlegraph/aesthetic-computer/oskiewar-cull"><img src="https://agentmods.dev/badge/skills/whistlegraph/aesthetic-computer/oskiewar-cull.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00072 | $0.01465 |
| Opus 5.5 | $0.00029 | $0.00586 |
| Sonnet 5.5 | $0.00014 | $0.00293 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
oskiewar-cull 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oskiewar reel cull
Meta's Graph API can publish a reel and report on it. It cannot delete one.
That is not an oversight in this pipeline — there is no endpoint — so the only
road to deleting a reel is a browser, and trim.mjs is deliberately built with
no Instagram login and no deletion path at all. It reports; something else acts.
This skill is that something else. It is you, in Chrome, holding a work list that a read-only tool produced.
The account has ~49.5k followers and deletion is irreversible. Nothing here deletes without a fresh yes from @jeffrey against the actual list.
1. Refresh, then read the list
cd ~/aesthetic-computer
set -a; . vault/oskiewar/instagram.env; set +a # OSKIEWAR_IG_TOKEN
node xbox/live/marketing/reel.mjs --insights # views AND permalinks
node xbox/live/marketing/trim.mjs # the work list
Refresh first, every time. The policy line is 1,000 views and reels keep earning views for weeks, so a candidate read off stale insights is a reel you may be deleting after it passed the bar. Insights older than a day or two are not good enough to delete on.
--insights is also what fills in permalink. A candidate printed with no
permalink recorded has nowhere for you to go: run the insights pass and ask
again.
node xbox/live/marketing/trim.mjs --json gives the same list as data.
2. Read what the misses mean before deleting them
A reel answering error subcode 33 — "does not exist, cannot be loaded due to
missing permissions" — during the refresh is already deleted, as long as
other reels refreshed fine on the same token. Those are ghosts, not candidates.
Do not go looking for them in Chrome; they are gone.
Check that the ghost is recorded (deletedAt in ledger.json). If it is not,
that is bookkeeping, not a cull.
3. Get a yes
Show @jeffrey the candidates — date, views, watch time, skip rate, segment — and wait. Deleting a reel is outward-facing and cannot be undone. A prior "go ahead" does not carry to a list he has not seen.
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.
- 1mo ago Changed · +19 lines dcab187ee36e
- 1mo ago First seen · 110 lines · 72 tokens per session scan A 2fbd4297ca47
oskiewar-cull is a skill published in the GitHub repository whistlegraph/aesthetic-computer (91 stars, last pushed yesterday), licensed ISC. It adds 72 tokens to every session and 1,465 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-14.
oskiewar-cull compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| oskiewar-cullwhistlegraph/aesthetic-computer | Skill | 91 | yesterday | ISC | A | 72 | Claude Code |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 12d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 911 | 3d ago | MIT | A | 40 | Claude Code |