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 takoyaro/the-agency --skill writinggit clone --depth 1 https://github.com/takoyaro/the-agencyWrote 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/takoyaro/the-agency/writing)<a href="https://agentmods.dev/skills/takoyaro/the-agency/writing"><img src="https://agentmods.dev/badge/skills/takoyaro/the-agency/writing/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/takoyaro/the-agency/writing"><img src="https://agentmods.dev/badge/skills/takoyaro/the-agency/writing.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 | $0.00121 | $0.00880 |
| Opus 5 | $0.00060 | $0.00440 |
| Sonnet 5 | $0.00024 | $0.00176 |
| Haiku 4.5 | $0.00012 | $0.00088 |
Grade A, and why
writing 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 11d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing
This skill supplies two things a writer doesn't hold in their head: the format standards for common documents, and a reference for catching AI-slop on an edit pass.
It does not set the voice. The register and tone are the writer's judgment — terse where terse is right, room to breathe where it's earned. What follows are standards and checks to write against, never a house style to write in. Match the piece to its reader first; then apply these.
1. Format standards — apply these
Don't improvise a format that already has a standard. Identify the document type and read its reference before drafting.
| Writing this | Read first |
|---|---|
| README | references/readme.md |
| CHANGELOG / version bump | references/changelog.md |
| Commit message | references/commit.md |
| Pull request description | references/pull-request.md |
| Release notes | references/release-notes.md |
These are the non-negotiable part: a changelog is Keep a Changelog, a version bump is semver. The skeletons in each reference are the target shape.
2. Anti-slop edit pass — a reference, not a rulebook
After a draft exists, check it against the tells. The full catalog — verbatim tell-strings, failure modes, before/after, sources — is in references/anti-slop.md; load it for anything heavier than a quick read.
Two things govern the whole pass:
- Density, not tokens. The tell is co-occurrence — three markers clustered in a paragraph — not any single word. A lone em-dash is fine; one "crucial" is fine. Never run a blocklist: a word-banned draft is its own kind of slop.
- Weigh every cut against register. On a terse document (commit, changelog, PR) cut hard — there's no tone to protect. On a piece that earns warmth (a post-mortem, an announcement, a README that greets a stranger), a sentence may carry tone rather than a fact. That is not slop; that is the writing. Keep it.
High-signal checks to run from memory (full tables in the reference):
What ships with it
6 files 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.
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.
- 11d ago First seen · 50 lines · 121 tokens per session scan A 117b59979844
writing is a skill published in the GitHub repository takoyaro/the-agency (1 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 880 once invoked, about $0.0006 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.
Other skills, from other repositories
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
goal-ledger-conductor
Own a long-horizon goal end to end while tracking it in the work ledger - decompose it into items, stand up one session per item, read each worker's reported status as structured data rather than as a transcript, verify claims with the acceptance evaluator, and decide each next round until the goal is met or a stop…
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…