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 skills add mkupermann/throughline --skill examplegit clone --depth 1 https://github.com/mkupermann/throughlineWrote 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/mkupermann/throughline/example)<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>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 5.1 | $0.00022 | $0.00816 |
| Opus 5 | $0.00011 | $0.00408 |
| Sonnet 5 | $0.00004 | $0.00163 |
| Haiku 4.5 | $0.00002 | $0.00082 |
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.
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
- Detects the current project from the working directory path or an explicit argument.
- Queries
memory_chunksfor decisions, patterns, insights and project context. - Queries
projectsfor team contacts and stored decisions. - Queries
entitiesfor key people and technologies associated with the project. - 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;
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.
- 2d ago First seen · 123 lines · 22 tokens per session scan A c266b0cacbf9
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.
Other skills, from other repositories
remnic-memory-workflow
Shared memory workflow for Claude Code agents connected to Remnic — recall before acting, observe during work, remember at the end. Trigger phrases include "what do you remember about", "save this for later", "any context from last time".
remnic-recall
Search Remnic memories by natural-language query. Trigger phrases include "what do you remember about", "recall anything on", "have we discussed".
remnic-remember
Store a durable memory in Remnic so every connected agent can recall it. Trigger phrases include "remember this", "save this for later", "add a note that".
remnic-search
Run a deep full-text search across every Remnic memory. Trigger phrases include "search memories for", "find anything about", "deep search".
remnic-status
Check the health of the Remnic daemon, stores, and connected clients. Trigger phrases include "is remnic running", "check memory status", "daemon health".
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.