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/dcostenco/prism-coder/prism-startupnpx skills add dcostenco/prism-coder --skill prism-startupgit clone --depth 1 https://github.com/dcostenco/prism-coderWrote 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/dcostenco/prism-coder/prism-startup)<a href="https://agentmods.dev/skills/dcostenco/prism-coder/prism-startup"><img src="https://agentmods.dev/badge/skills/dcostenco/prism-coder/prism-startup.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 | $0.00052 | $0.01012 |
| Opus 5 | $0.00026 | $0.00506 |
| Sonnet 5 | $0.00010 | $0.00202 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
prism-startup 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prism Startup
Use this skill once, on the first user turn of a conversation. A greeting such as "hi", "hello", or "ready?" is still a first user turn and must activate it. Do not run it again after startup context has already been shown in the same conversation.
Portable native-skill activation starts when the host processes the first user turn. It cannot display anything before the developer sends that first input. That first-turn behavior is the cross-host contract.
Provisioning contract
This skill ships with the prism plugin, alongside the Prism MCP server
registration. The prism connect CLI installs the same protected skill for
hosts configured that way; when both are present, the re-entry rule above keeps
startup to a single display. Startup must not modify a host's lifecycle
configuration. The skill remains available on every subscription tier, and it is
intentionally absent from session skill routing so loading context cannot inject
this startup procedure recursively.
First action: bootstrap context
Before greeting the developer or answering their task:
- If
session_bootstrapis available, call it with no arguments. Do not guess a project, role, developer name, or context depth. - If
session_bootstrapis unavailable butsession_load_contextis available, callsession_load_contextfor the current project and omit thelevelargument. Use the repository or workspace name as the project; useprism-mcponly when no project can be derived. - If MCP tools are unavailable but the
prismCLI is available, runprism load <project> --jsonand omit--level. - If the first attempt fails, correct the parameters and retry once. If the
retry and fallback both fail, display exactly:
⚠️ *Session context is temporarily unavailable.*
The level must be omitted in every startup path. Prism resolves the current dashboard setting instead of allowing this static skill to override it.
Context-depth contract
Render only the data returned for the resolved depth:
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.
- 5d ago First seen · 96 lines · 52 tokens per session scan A fa6bc4091fa4
prism-startup is a skill published in the GitHub repository dcostenco/prism-coder (157 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,012 once invoked, about $0.0003 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
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
qmclaw-workbench
使用 OpenQuantum 的 QMClaw Local Tool 对超导量子比特 S21、能谱、Rabi、Ramsey、T1、SingleShot、DRAG、π 脉冲、功率偏移、Delta 和 RB 等 13 类测控实验做有界、确定性的本地模拟，并组织单比特调校工作流。用于实验规划、接口联调、教学和无硬件预检；不连接 LabRAD/lqms、真实仪器或量子云，不修改校准参数，也不替代 Scientific Validator。.
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
event-staffing-ordering
Order W-2 event staff for US/CA events through TempGuru.
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…