Agent skill

Prime Context

by swingerman in swingerman/engineer

Use before starting pipeline work on a Ready feature the agent hasn't worked yet.

MITAuto-check passed

Install Prime Context

skills CLI
$ npx skills add swingerman/engineer --skill prime-context -a claude-code

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

GitHub CLI
$ gh skill install swingerman/engineer prime-context --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/swingerman/engineer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/engineer/skills/prime-context .claude/skills/prime-context && 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
prime-context
GitHub stars
154
Token cost
~865 tokens
SKILL.md length
393 words
Files
1
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Use before starting pipeline work on a Ready feature the agent hasn't worked yet.

  • Works in 5 steps: Resolve + locate — resolve the… → Silent batch load — without narrating:… → Orient — give a concise summary:… → …
  • — /engineer.prime-context
  • SKILL.md covers When to use, Workflow, Handoff and References
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prime Context is an agent skill from swingerman/engineer. Use before starting pipeline work on a Ready feature the agent hasn't worked yet. Triggers — "/engineer.prime-context", "prime context", "load context before we start", "get up to speed on feature X".

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Disciplined Agentic Engineering — a methodology kit for Claude Code: acceptance-test-first specs, explicit checkpoints, and autonomy you can actually leave running. The engineer… The licence is MIT.

When your agent uses it

  • — /engineer.prime-context
  • Load context before we start
  • Get up to speed on feature X

Example prompts

  • “t worked yet. Triggers —”
  • “prime context”
  • “load context before we start”
  • “/prime-context”

Workflow steps

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

  1. Resolve + locate — resolve the methodology root + manifest via ${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py (see references/resolving.md)…
  2. Silent batch load — without narrating: feature.md, CHARTER.md, manifest.yml, prior handoffs/ (especially the originating *-discuss.md)…
  3. Orient — give a concise summary: outcome, scope, autonomy level (+ charter cap), key prior decisions, related code, relevant ADRs.
  4. One prompt — ask exactly one question: anything else to load? If the user names a new code pointer, load it and offer to add it to…
  5. Breadcrumb handoff — emit a tiny handoff recording what was loaded.

What it can do on your machine

Read from SKILL.md and the folder at commit 32947eb. 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

    Links to these hosts (documentation or services it may open):

    • notion.so

    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

Prime Context loads about 865 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 393 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~865

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 swingerman/engineer at commit 32947eb, republished under its MIT licence (© swingerman). 393 words, ~865 tokens.

Download SKILL.mdSave it as .claude/skills/prime-context/SKILL.md (or your agent's skills folder).
name
prime-context
description
Use before starting pipeline work on a Ready feature the agent hasn't worked yet. Triggers — "/engineer.prime-context", "prime context", "load context before we start", "get up to speed on feature X".

prime-context

Load working memory before pipeline work on a Ready feature — the convergent counterpart to discuss. Forked from superpowers:brainstorming but inverted: no exploration, just loading and orienting. Produces no artifact.

When to use

A prep step (not a checkpoint) between feature-init and discover-acs, on any feature the agent hasn't already worked this session.

Skip when: the agent just created the feature this session (context already warm). Not for: exploring whether a feature is worth doing (discuss).

Workflow

  1. Resolve + locate — resolve the methodology root + manifest via ${CLAUDE_PLUGIN_ROOT}/scripts/dae_resolve.py (see references/resolving.md); locate the feature (slug arg or branch name). Reject if no folder / no feature.md. Layout disambiguation: if the project has BOTH a features/NNN-*/ and a specs/NNN-*/ tree (a speckit migration in progress), state which holds this feature's artifacts; and if more than one acceptance-IR convention is present (features/NNN/.build/spec.json vs an acceptance-pipeline/ir/ per-GWT layout), name the one this feature uses — so the load doesn't rediscover the split ad-hoc. (speckit-consolidate unifies it.)
  2. Silent batch load — without narrating: feature.md, CHARTER.md, manifest.yml, prior handoffs/ (especially the originating *-discuss.md), and the files named in feature.md's "Related code / design pointers". When loading those code pointers, prefer LSP — documentSymbol for file shape, hover for signatures/types, workspaceSymbol to pull in the symbols they reference — over reading whole files blind, when an LSP MCP capability is available; fall back to grep + Read otherwise. See ${CLAUDE_PLUGIN_ROOT}/references/code-lookup.md.
  3. Orient — give a concise summary: outcome, scope, autonomy level (+ charter cap), key prior decisions, related code, relevant ADRs.
  4. One prompt — ask exactly one question: anything else to load? If the user names a new code pointer, load it and offer to add it to feature.md. Then stop — prime-context orients, it does not interview.
  5. Breadcrumb handoff — emit a tiny handoff recording what was loaded.
Show full SKILL.md (101 more words)Show less

Re-invocation re-loads fresh (no incremental diffing).

Handoff

Emit per ${CLAUDE_PLUGIN_ROOT}/references/handoff-summary.md. checkpoint: null; artifacts: []; human_action_needed: no; recommended_next: "/engineer.discover-acs".

Always emit a breadcrumb. Earlier versions produced no handoff because prime-context creates no artifact. Users expect a breadcrumb after every skill invocation (distbute Jun 4: "emit the handoff") — surprising them with "no artifact by design" breaks the agentic-summary contract. The breadcrumb records: which feature was primed, what files were loaded, any new pointer added to feature.md, and the next recommended skill. Body can be one paragraph — frontmatter is the load-bearing part for progress-log propagation.

References

© swingerman, MIT. 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 engineer/skills/prime-context of swingerman/engineer.

Open the folder on GitHubat commit 32947eb

Compare with similar skills

Prime 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.

Prime Context compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prime Context this skillswingerman/engineer154—~865Automated safety check: PassMIT
StartDonchitos/Claude-Code-Game-Studios26k—~6.4kAutomated safety check: PassMIT
Session Start Hookasgeirtj/system_prompts_leaks69k1 repos~1.2kAutomated safety check: PassCC0-1.0
Where Do I Startmohitagw15856/pm-claude-skills1.4k—~912Automated safety check: PassMIT
Prime Numbersparcadei/Continuous-Claude-v33.9k1 repos~405Automated safety check: NotesMIT
Cold Start Interviewanthropics/claude-for-legal9.6k3 repos~11kAutomated safety check: PassApache-2.0

Similar skills

  • Start

    Donchitos/Claude-Code-Game-Studios

    First-time onboarding — asks where you are, then guides you to the right workflow.

    26k GitHub stars~6.4k tokensUpdated 8 days ago
    Game DevelopmentAuto-check passed
  • Session Start Hook

    asgeirtj/system_prompts_leaks

    Creating and developing startup hooks for Claude Code on the web.

    69k GitHub starsUsed in 1 repo~1.2k tokens
    DevelopmentAuto-check passed
  • Where Do I Start

    mohitagw15856/pm-claude-skills

    Turn a chaotic pile of everything-in-your-head into one clear first action — the antidote to the paralysis of too much at once.

    1.4k GitHub stars~912 tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Prime Numbers

    parcadei/Continuous-Claude-v3

    Problem-solving strategies for prime numbers in graph number theory

    3.9k GitHub starsUsed in 1 repo~405 tokens
    Research & ScienceAuto-check: notes
  • Cold Start Interview

    anthropics/claude-for-legal

    Official

    Run the cold-start interview to learn your IP practice and write your practice profile.

    9.6k GitHub starsUsed in 3 repos~11k tokens
    Agent WorkflowsAuto-check passed
  • Cold Start Interview

    anthropics/claude-for-legal

    Official

    Cold-start setup — learns your jurisdictional footprint and escalation rules from your handbook and termination memos.

    9.6k GitHub starsUsed in 2 repos~8k tokens
    Agent WorkflowsAuto-check passed

More from swingerman/engineer

All 27 skills in this repo
  • Crap Analyzer

    swingerman/engineer

    A skill your agent uses to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods.

    154 GitHub stars~1.2k tokensUpdated 14 days ago
    Auto-check passed
  • Atdd Mutate

    swingerman/engineer

    A skill your agent uses to add a third validation layer to the ATDD workflow — after acceptance tests verify WHAT and unit tests verify HOW, mutation testing verifies the tests actually catch bugs.

    154 GitHub stars~2.7k tokensUpdated 14 days ago
    Auto-check passed
  • Fix

    swingerman/engineer

    A skill your agent uses to drive a bug fix from first report through close, with a "why didn't we catch it?" loop at the end.

    154 GitHub stars~3k tokensUpdated 14 days ago
    Auto-check passed
  • Atdd

    swingerman/engineer

    A skill your agent uses to drive feature work through the Acceptance Test Driven Development workflow — Given/When/Then specs before code, a project-specific test pipeline, and two parallel test…

    154 GitHub stars~2.8k tokensUpdated 14 days ago
    Auto-check passed
  • Harden

    swingerman/engineer

    Use after a feature passes Light Verify (CP7), to prove the tests actually catch bugs and, where the code warrants it, to formally check its invariants — Checkpoint 8.

    154 GitHub stars~1.8k tokensUpdated 14 days ago
    Auto-check passed
  • Next

    swingerman/engineer

    Use at the start of a work session, or any time the question is "what should I pick up now" across the whole project.

    154 GitHub stars~3k tokensUpdated 14 days ago
    Auto-check passed

Questions about Prime Context

What does Prime Context do?

Use before starting pipeline work on a Ready feature the agent hasn't worked yet. Prime Context is an agent skill from swingerman/engineer. Use before starting pipeline work on a Ready feature the agent hasn't worked yet.

When should I use Prime Context?

Prime Context fits situations like: — /engineer.prime-context; load context before we start; get up to speed on feature X.

How do I install Prime Context in Claude Code?

Run `npx skills add swingerman/engineer --skill prime-context -a claude-code`. Or copy the skill folder (engineer/skills/prime-context in swingerman/engineer) into .claude/skills/prime-context in your project. Claude Code loads it when a task matches its description.

How do I install Prime Context in Codex?

Run `npx skills add swingerman/engineer --skill prime-context -a codex`. Or copy the skill folder (engineer/skills/prime-context in swingerman/engineer) into .agents/skills/prime-context in your project. Codex loads it when a task matches its description.

Can I use Prime 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 swingerman/engineer --skill prime-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prime-context, .gemini/skills/prime-context, .github/skills/prime-context and .opencode/skills/prime-context in your project.

What does Prime Context need to run?

SKILL.md names no scripts, command-line tools or credentials: Prime Context is instructions for the agent only.

Does Prime Context access the network?

SKILL.md names 1 domain. As links in the text: notion.so. This is read from the text; nothing was executed.

Is Prime 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 Prime Context use?

Prime Context is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prime Context use?

About 865 tokens (SKILL.md is roughly 3.5k 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 Prime Context?

Skills that share tags, products or a category with Prime Context: Start (Donchitos/Claude-Code-Game-Studios, 26k stars), Session Start Hook (asgeirtj/system_prompts_leaks, 69k stars), Where Do I Start (mohitagw15856/pm-claude-skills, 1.4k stars) and Prime Numbers (parcadei/Continuous-Claude-v3, 3.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prime Context?

swingerman (a GitHub user) maintains it in swingerman/engineer, which has 154 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on September 23, 2026.

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