project-context-loader

project-context-loader is a skill for Claude Code, Codex from mkupermann/throughline. It costs 22 tokens per session (816 once invoked), scanned A, original, MIT.

A project-memory loader that retrieves stored decisions, notes, contacts, and related technologies for the current project. It can infer the project from the working folder.

In plain words
What is it for?
Loading prior project context before coding and answering questions about past decisions, people, and technologies.
Why use it?
It reduces the need to repeat project background at the start of every coding session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Claude Code.

Good fit Loading prior project context before coding and answering questions about past decisions…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mkupermann/throughline/example
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.

Any agent
npx skills add mkupermann/throughline --skill example
Clone the repo
git clone --depth 1 https://github.com/mkupermann/throughline

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for project-context-loader

README.md
[![agentmods](https://agentmods.dev/badge/skills/mkupermann/throughline/example.svg)](https://agentmods.dev/skills/mkupermann/throughline/example)
Your own site
<a href="https://agentmods.dev/skills/mkupermann/throughline/example"><img src="https://agentmods.dev/badge/skills/mkupermann/throughline/example.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00022 $0.00816
Opus 5 $0.00011 $0.00408
Sonnet 5 $0.00004 $0.00163
Haiku 4.5 $0.00002 $0.00082

Measured 2d ago against content hash c266b0cacbf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

project-context-loader 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.

examples/example_skill.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Context Loader

Retrieves and summarises everything the memory database knows about the current project before you start coding. Eliminates the "cold-start" problem where each Claude Code session begins with zero context.

What it does

  1. Detects the current project from the working directory path or an explicit argument.
  2. Queries memory_chunks for decisions, patterns, insights and project context.
  3. Queries projects for team contacts and stored decisions.
  4. Queries entities for key people and technologies associated with the project.
  5. Presents a structured summary and offers to answer follow-up questions.

Usage

load context for fintech-api
what do I know about project-aurora?
project context acme-web

If you call it without an argument the skill infers the project name from the current working directory (last path segment).

Example output

## Context for: fintech-api
Last session: 2026-04-01  |  17 memory chunks  |  3 decisions

### Key decisions
1. Use idempotency keys on all payment endpoints (2025-12-02)
2. Encrypt PII at application layer, not DB-only (2026-01-21)
3. Rate-limit /reconcile to 10 req/min per client (2026-02-10)

### Team contacts
- Alex Kim — Engineering Manager ([email protected])
- Priya Nair — Security Auditor; requires written approval for auth/crypto changes

### Patterns to remember
- N+1 fix: always bulk-fetch with ANY($1) in batch endpoints
- Reconciliation p99: was 8.2s, now 340ms after index + bulk query fix

### Error solutions on record
- SSL connection drop: set keepalives_idle=30 in psycopg2 pool config

Implementation

The skill calls the following SQL at startup. Copy and adjust as needed:

-- Load active memory chunks for the project
SELECT
    category,
    content,
    confidence,
    tags,
    created_at::date AS date
FROM public.memory_chunks
WHERE project_name = :project_name
  AND status       = 'active'
ORDER BY category, confidence DESC;

-- Load contacts and decisions from the projects table
SELECT
    contacts,
    decisions
FROM public.projects
WHERE name = :project_name;

-- Load related entities
SELECT
    entity_type,
    name,
    attributes,
    mention_count
FROM public.entities
WHERE project_name = :project_name
ORDER BY mention_count DESC
LIMIT 10;

Read the full file on GitHub · 123 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 · 123 lines · 22 tokens per session scan A c266b0cacbf9

Subscribe to this mod's changes

project-context-loader is a skill published in the GitHub repository mkupermann/throughline (21 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 816 once invoked, about $0.0001 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 2026-09-04.