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 agentmods add skills/anmarhani/swarmvault/swarm-writenpx skills add AnmarHani/SwarmVault --skill swarm-writegit clone --depth 1 https://github.com/AnmarHani/SwarmVaultWrote 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/anmarhani/swarmvault/swarm-write)<a href="https://agentmods.dev/skills/anmarhani/swarmvault/swarm-write"><img src="https://agentmods.dev/badge/skills/anmarhani/swarmvault/swarm-write.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 | $0.00105 | $0.03336 |
| Opus 5 | $0.00053 | $0.01668 |
| Sonnet 5 | $0.00021 | $0.00667 |
| Haiku 4.5 | $0.00011 | $0.00334 |
Grade A, and why
swarm-write 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 4d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
swarm-write — writing for humans
Most agent-written copy fails the same way: no voice, even rhythm, filler detail, and the machinery showing through. This skill is not a banned-word filter. Filters date fast and flatten every voice into one texture. Write from a stance, then subtract.
Jurisdiction (check this first)
| lane | reader | what applies |
|---|---|---|
| end-user text | humans who did not ask for it | all of this skill |
| agent-facing (prompts, tickets, queue, skill files) | models | machine lane, unchanged |
| project docs (SRS, ADRs, specs) | owner + future agents | clear and complete, no voice work, no marketing |
| code and the prose inside it | engineers | §Code lane only |
Outside the first row, stop reading and write as you normally would.
1. Name the reader before writing a word
One line, not an interview: who reads this, what they do next, what they already know, what makes them quit. Most agent copy is bad because it was written for whoever asked, not whoever reads.
Write to one person, not an audience. "A backend dev at a 20-person startup who just got paged" produces sharper prose than "developers," every time. Specificity in the reader creates specificity in the writing.
2. Voice
First: whose voice is it? The surface decides, and getting this wrong personalizes what shouldn't be personal:
- Personal (the user's posts, portfolio, personal brand, a project that is them) → the user's voice. Profile, menu candidates, samples — everything below applies.
- Product (an app, tool, or service built for an audience) → the product's voice,
derived from audience + category + brand direction, not from the user's persona. If
swarm-design-uichose a brand direction, that choice is the voice input — derive from it, don't re-interview. Store as the project'svoice.mdwithowner: product. The user approves it once like any design decision; nobody's personal taste is mined for it. - UI microcopy (tooltips, errors, buttons, empty states) → automatic, always. Product
voice + the reader's emotional state (
references/ui-copy.md) set the register. Never run voice candidates for a tooltip.
What ships with it
5 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.
- 4d ago First seen · 245 lines · 105 tokens per session scan A 769571b5b519
swarm-write is a skill published in the GitHub repository AnmarHani/SwarmVault (5 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 3,336 once invoked, about $0.0005 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
architect-review
use when user ask to review spec.
data-integrity-review
Data integrity specialist for schema correctness, owner isolation, projections, hash chains, log separation, snapshots, and replay consistency. Use when validating that data remains correct under sync and persistence rules.
coder
Use when the task is to implement code changes from an assigned scope, including bug fixes, follow-ups, rejects, or current-worktree repair.
edge-case-review
Use when stress-testing failure paths, race conditions, reconnects, duplicate or out-of-order events, stale state, permission bypasses, crash recovery, or breaking the system under hostile chaos conditions.
spec-to-svg-flow-map
Chuyển spec sản phẩm, tính năng, UI, backend, auth, sync, lifecycle, external contract, hoặc spec đa nhánh thành SVG flow map ngữ nghĩa có metadata máy đọc được, source coverage, render từng flow, gap detection, verification report, và trạng thái BLOCKED hoặc READYFOROWNERREVIEW. Dùng khi cần biến spec thành flow map…
system-architect
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.