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 0spoon/seamless --skill seam-onboardgit clone --depth 1 https://github.com/0spoon/seamlessWrote 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/0spoon/seamless/seam-onboard)<a href="https://agentmods.dev/skills/0spoon/seamless/seam-onboard"><img src="https://agentmods.dev/badge/skills/0spoon/seamless/seam-onboard/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/0spoon/seamless/seam-onboard"><img src="https://agentmods.dev/badge/skills/0spoon/seamless/seam-onboard.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 | $0.00077 | $0.01857 |
| Opus 5.5 | $0.00031 | $0.00743 |
| Sonnet 5.5 | $0.00015 | $0.00371 |
| Haiku 4.5 | $0.00008 | $0.00186 |
Grade A, and why
seam-onboard 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard Seamless
Install concise Seamless awareness for the agent client running this skill. Do not edit an instruction file until the user chooses the target and sees what will be added.
1. Resolve the current client
Use the client you are currently running in, not whichever client directories happen to exist on disk:
| Client | Install profile | Global instructions | Project instructions | Invocation | Skill directory |
|---|---|---|---|---|---|
| Codex | codex |
$CODEX_HOME/AGENTS.md when set; otherwise ~/.codex/AGENTS.md |
./AGENTS.md |
$seam-onboard |
$CODEX_HOME/skills/seam-onboard when set; otherwise ~/.codex/skills/seam-onboard |
| Claude Code | claude |
$HOME/.claude/CLAUDE.md |
./CLAUDE.md |
/seam-onboard |
$HOME/.claude/skills/seam-onboard |
If the runtime does not make the current client clear, ask the user which of these two clients is running. Do not infer it from the presence of both homes.
2. Confirm the integration
Check the selected client's registration:
- Codex:
codex mcp get seamless - Claude Code:
claude mcp get seamless
If it is absent, explain that the next command installs that client's Seamless hooks, MCP registration, and maintained skills, then run:
seamlessd install-hooks --client <profile>
Use codex or claude for <profile>. Stop and surface the error if the
command fails. Never discover, print, paste, or place the bearer key in a client
command: the installer uses seam mcp-proxy for Codex and seam mcp-headers
for Claude Code so the key stays in Seamless's config.
For Claude Code, inspect claude mcp get seamless. If it reports a project or
local registration instead of user scope, tell the user it must be migrated,
run claude mcp remove seamless, then run the install command above with the
claude profile. Codex's registration is already user-level in its config.
3. Inspect and ask for the target
Before asking, inspect both candidate instruction files for the current client.
Report whether each exists and whether it already contains
<!-- seam-onboard:start -->. Explain that you will append one marker-wrapped
section describing when to use shared memories, notes, sessions, plans, and
tasks; no other instruction text will change.
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 First seen · 118 lines · 77 tokens per session scan A 15c5d50528a8
seam-onboard is a skill published in the GitHub repository 0spoon/seamless (5 stars, last pushed 25d ago), licensed MIT. It adds 77 tokens to every session and 1,857 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 2026-08-31.
Other skills, from other repositories
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.