New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Prism Startup Context

by dcostenco in dcostenco/prism-coder

Loads Prism session memory on the first user turn, greets the developer by their configured name and shows recent-session context at the configured depth.

Apache-2.0Auto-check passedAgent Workflows

Install Prism Startup Context

skills CLI
$ npx skills add dcostenco/prism-coder --skill prism-startup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dcostenco/prism-coder prism-startup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dcostenco/prism-coder.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/prism/skills/prism-startup .claude/skills/prism-startup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prism-startup
GitHub stars
158
Token cost
~1.4k tokens
SKILL.md length
783 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Loads Prism session memory on the first user turn, greets the developer by their configured name and shows recent-session context at the configured depth.

  • Works in 4 steps: If session_bootstrap is available, call… → If session_bootstrap is unavailable but… → If MCP tools are unavailable but the… → …
  • Starting any conversation in a project that uses Prism session memory
  • SKILL.md covers Provisioning contract, First action: bootstrap context, Context-depth contract and Greeting and context output, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill activates once, on the first user turn of a conversation, even when that turn is only a greeting, and does not repeat after startup context has been shown. Before greeting or answering, the agent calls session_bootstrap with no arguments. If that is unavailable it calls session_load_context for the repository or workspace project, and failing that runs the prism load command with JSON output. One retry is allowed, after which a fixed warning says that context is temporarily unavailable.

The depth is never passed by the skill, because Prism resolves the current dashboard setting. Quick depth greets by name and shows the compact current state with open TODOs or keywords, standard adds the last summary and up to five recent sessions, and the excerpt is cut off before deep. A section also explains recovering when a save is refused with context_not_loaded. It ships with the prism plugin and its MCP server.

When your agent uses it

  • Starting any conversation in a project that uses Prism session memory
  • Resuming work with recent sessions and open TODOs shown up front
  • Recovering when a save is refused with context_not_loaded

Example prompts

  • “Hello, let's pick up where we left off yesterday.”
  • “Load my Prism context for this project before we begin.”
  • “Show my recent sessions and open TODOs, then wait for my task.”

Requirements

  • The Prism MCP server or the `prism` CLI
  • A project with saved Prism session memory

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. If session_bootstrap is available, call it with no arguments. Do not guess
  2. If session_bootstrap is unavailable but session_load_context is
  3. If MCP tools are unavailable but the prism CLI is available, run
  4. If the first attempt fails, correct the parameters and retry once. If the

What it can do on your machine

Read from SKILL.md and the folder at commit 6f43322. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prism Startup Context loads about 1.4k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 783 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dcostenco/prism-coder at commit 6f43322, republished under its Apache-2.0 licence (© dcostenco). 783 words, ~1,398 tokens.

Download SKILL.mdSave it as .claude/skills/prism-startup/SKILL.md (or your agent's skills folder).
name
prism-startup
description
Activate on the first user turn of every conversation, including greetings. Load Prism context using the user's configured project and quick, standard, or deep depth, then greet the developer by their configured agent name and show the matching recent-session context.

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. This re-entry rule covers startup only; a save refused with context_not_loaded is recovered as described under "Recovering from context_not_loaded" below.

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:

  1. If session_bootstrap is available, call it with no arguments. Do not guess a project, role, developer name, or context depth.
  2. If session_bootstrap is unavailable but session_load_context is available, call session_load_context for the current project and omit the level argument. Use the repository or workspace name as the project; use prism-mcp only when no project can be derived.
  3. If MCP tools are unavailable but the prism CLI is available, run prism load <project> --json and omit --level.
  4. 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:

  • quick: greet with the configured name and show the compact current state, including open TODOs or keywords when present. Do not claim session summaries were absent; quick intentionally does not fetch them.
  • standard: also show the last summary and up to five recent sessions.
  • deep: also show the complete returned session history, up to fifty entries, including the extra decisions, TODOs, and changed-file detail supplied by Prism.

Do not make a second load call to expand the selected depth. An empty field is different from a field intentionally omitted at the selected depth.

Show full SKILL.md (363 more words)Show less

Greeting and context output

If session_bootstrap returns a ready-to-display greeting/context block, print the complete bootstrap result verbatim as the entire first-turn startup display, before any task answer. Do not summarize, paraphrase, rename headings, reformat, or omit any returned section. Preserve its order and line content.

If no ready-to-display block is returned, render the structured fallback result in this order:

  1. Hi, <agent_name>. using the configured agent_name. If it is empty, use Hi. without inventing a name.
  2. **Last session:** <last_summary> when the selected depth returned it.
  3. **Open TODOs:** followed by the returned TODOs, when present.
  4. **Recent sessions:** for standard results or **Session history:** for deep results, preserving the returned order.

When the first user input is only a greeting, stop after the verbatim startup display. If only the structured fallback was available, stop after that structured startup display. Do not add another greeting, question, acknowledgement, or other prose. When the first input contains a task, continue directly into that task after the startup display.

Foundational skill verification

Context loading may return entitled [📜 SKILL: <name>] blocks. Use only the skills explicitly reported as provisioned or returned in those blocks. Never guess a package name, request a missing package, or treat a package from an old session as currently entitled. Paid behavioral and engineering packages are delivered by the authenticated manifest; the public startup path relies on the compact safety and evidence contract in the MCP server instructions.

For bug reports or screenshots, run a real diagnostic before explaining the cause. Never report "done", "fixed", or "working" without observable verification.

Recovering from context_not_loaded

Startup runs once, but a later session_save_ledger or session_save_handoff can still be refused with context_not_loaded: after a long idle gap, after a restart, or for a project that startup did not load. That is not a second startup and the re-entry rule above does not apply. Call session_load_context with the same project and the same conversation_id as the refused save, then retry the save once. Do not repeat session_bootstrap or print a startup display for it. If the reload or the retry fails, tell the user; a local note is a fallback after that, never a substitute for the reload.

© dcostenco, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/prism/skills/prism-startup of dcostenco/prism-coder.

Open the folder on GitHubat commit 6f43322

Compare with similar skills

Prism Startup Context next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prism Startup Context compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prism Startup Context this skilldcostenco/prism-coder158—~1.4kAutomated safety check: PassApache-2.0
Memori MCP Memory UsageMemoriLabs/Memori17k—~3.8kAutomated safety check: PassMIT
Engram MemoryPatdolitse/piia-engram163—~1.3kAutomated safety check: PassAGPL-3.0-or-later
Mnemosjeremylongshore/tons-of-skills-marketplace2.8k—~3.1kAutomated safety check: PassMIT
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT
agentmemory Setup and Diagnosticsrohitg00/agentmemory29k—~1kAutomated safety check: NotesApache-2.0

Similar skills

  • Memori MCP Memory Usage

    MemoriLabs/Memori

    Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.

    17k GitHub stars~3.8k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

  • Engram Memory

    Patdolitse/piia-engram

    Routes continuity and recall requests to Engram, a local-first MCP memory and identity layer that saves user-approved lessons, decisions and playbooks.

    163 GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Mnemos

    jeremylongshore/tons-of-skills-marketplace

    Persistent memory and learning-loop skills for AI coding agents using mnemos MCP tools.

    2.8k GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • MemPalace Setup and Operation

    MemPalace/mempalace

    Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    59k GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • agentmemory Setup and Diagnostics

    rohitg00/agentmemory

    Sets up and troubleshoots a local agentmemory install, covering the MCP connection, environment variables, ports, authentication and optional feature flags.

    29k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Qmd

    breferrari/obsidian-mind

    Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.

    5k GitHub stars~1.7k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

Works with

Categories

Questions about Prism Startup Context

What does Prism Startup Context do?

Loads Prism session memory on the first user turn, greets the developer by their configured name and shows recent-session context at the configured depth. The skill activates once, on the first user turn of a conversation, even when that turn is only a greeting, and does not repeat after startup context has been shown. Before greeting or answering, the agent calls session_bootstrap with no arguments.

When should I use Prism Startup Context?

Prism Startup Context fits situations like: starting any conversation in a project that uses Prism session memory; resuming work with recent sessions and open TODOs shown up front; recovering when a save is refused with context_not_loaded.

How do I install Prism Startup Context in Claude Code?

Run `npx skills add dcostenco/prism-coder --skill prism-startup -a claude-code`. Or copy the skill folder (plugins/prism/skills/prism-startup in dcostenco/prism-coder) into .claude/skills/prism-startup in your project. Claude Code loads it when a task matches its description.

How do I install Prism Startup Context in Codex?

Run `npx skills add dcostenco/prism-coder --skill prism-startup -a codex`. Or copy the skill folder (plugins/prism/skills/prism-startup in dcostenco/prism-coder) into .agents/skills/prism-startup in your project. Codex loads it when a task matches its description.

Can I use Prism Startup Context in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dcostenco/prism-coder --skill prism-startup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prism-startup, .gemini/skills/prism-startup, .github/skills/prism-startup and .opencode/skills/prism-startup in your project.

What does Prism Startup Context need to run?

SKILL.md names no scripts, command-line tools or credentials: Prism Startup Context is instructions for the agent only. Our summary lists: The Prism MCP server or the `prism` CLI; A project with saved Prism session memory.

Does Prism Startup Context access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Prism Startup Context safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prism Startup Context use?

Prism Startup Context is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prism Startup Context use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prism Startup Context?

Skills that share tags, products or a category with Prism Startup Context: Memori MCP Memory Usage (MemoriLabs/Memori, 17k stars), Engram Memory (Patdolitse/piia-engram, 163 stars), Mnemos (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and MemPalace Setup and Operation (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prism Startup Context?

dcostenco (a GitHub user) maintains it in dcostenco/prism-coder, which has 158 GitHub stars. The repository was last updated on October 10, 2026.

Source: dcostenco/prism-coder on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.