load-project-context

A project-context loading procedure for spec-driven development. It tells the agent which current project documents to read before planning, editing, fixing, reviewing, or documenting work.

In plain words
What is it for?
Use it before work in a project with area documentation to read the project map, area overview, current status, and any relevant specifications or runbooks.
Why use it?
It prevents the agent from working without the relevant project background while avoiding unnecessary archive reading. It also gives the agent an ordered way to find area-specific information.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/voytechg/spec-driven-development/load-project-context
Any agent
npx skills add VoytechG/spec-driven-development --skill load-project-context
Clone the repo
git clone --depth 1 https://github.com/VoytechG/spec-driven-development

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 689 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00689
Opus 5 $0.00016 $0.00345
Sonnet 5 $0.00006 $0.00138
Haiku 4.5 $0.00003 $0.00069

Measured 2d ago against content hash ccb39f560942, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

load-project-context 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 2d 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.

skills/load-project-context/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Load Project Context

Load only the active working context needed for the next task. Historical plans, decision records, run logs, and archives are reference material; search or read them only when the task asks for history or clearly revisits a previous choice.

Workflow

  1. Read AREAS.md at the project root. It lists every area with its Path: and Docs: entries plus a short prose description.
  2. Identify the touched area(s). Match the user's prompt and any quoted file paths against the Path: entries in AREAS.md. If multiple areas are involved, load each one.
  3. Read the area's <docsRoot>/README.md first. It states the area's purpose and the doc reading order.
  4. Load the active docs only:
    • implementation-status.md — always; it should be a compact current snapshot.
    • spec.md, product-spec.md, or the active specs/<date>-<feature>.md named by the README/status — when the work touches behavior, scope, schema, architecture, UX, or acceptance.
    • operations.md or another runbook — only when the work involves running, deploying, importing, exporting, retrying, or troubleshooting the area.
    • acceptance-criteria.md — only when the area keeps criteria separate from the spec and the task changes or verifies those criteria.
    • plans/<date>-<batch>.md — only when continuing or modifying that in-flight batch.
  5. Avoid history by default.
    • Do not read decisions/, logs/, archive/, or old plans during normal coding unless the README/status points to a specific current record or the task asks why something was chosen.
    • If you suspect a previous decision matters, use targeted search first. Search only history paths that exist, e.g. build a short candidate list from <docsRoot>/decisions, <docsRoot>/logs, and <docsRoot>/archive, then run rg -n "<topic>" ... and read only the matching file.
    • For onboarding, broad history review, or "did we already decide this?", use review-project-history instead of loading history into working context.
  6. State which areas and docs you used. Before drafting a plan or making edits, list them in your response so the human partner can confirm coverage.
  7. Seed a final task-list/checklist item using the host's task tool: "Run maintain-project-docs before claiming completion." Use TodoWrite in Claude Code, update_plan in Codex, or the local checklist mechanism in other agents.

Read the full file on GitHub · 37 lines

Changes

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.

  1. 2d ago First seen · 37 lines · 32 tokens per session scan A ccb39f560942

Subscribe to this mod's changes

load-project-context is a skill published in the GitHub repository VoytechG/spec-driven-development (4 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 689 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens