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 agentmods add agents/moabualruz/fulcrum/contextgit clone --depth 1 https://github.com/moabualruz/fulcrumWrote 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/agents/moabualruz/fulcrum/context)<a href="https://agentmods.dev/agents/moabualruz/fulcrum/context"><img src="https://agentmods.dev/badge/agents/moabualruz/fulcrum/context.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 | $0.00000 | $0.00638 |
| Opus 5 | $0.00000 | $0.00319 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
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 3d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
Application-layer reads and writes over AgentProfile rows: listing, upserting, masking secrets for the UI, and recording test outcomes. Inherits the parent service vocabulary (AgentProfile, AgentRun, Org) and only sharpens the terms that exist solely inside this folder.
Language
MaskedProfileRow:
A UI-safe projection of an AgentProfileRow where each authEnv value is replaced with a fixed-width mask, plus derived capabilities and sessions_count.
Avoid: Sanitized profile, redacted profile, view-model.
AuthEnvEntry:
One KEY=VALUE string inside AgentProfile.authEnvVars; parsed into a {key, maskedValue} pair for display.
Avoid: Credential, secret pair, env tuple.
Capability:
A tag (LLM, code, multi-modal, search, browser, general) derived from an AgentProfile.name heuristic; advisory UI hint only.
Avoid: Skill, feature, ability.
ProfileTestOutcome:
The boolean verdict (testPassed) plus lastTestedAt timestamp recorded by testProfileAction; emits an agent_profile / tested event.
Avoid: Health check, smoke test result.
AgentProfilesPageData:
The bundle (profiles, projects, tasks) assembled for the profile-list UI route.
Avoid: Page payload, view data.
Relationships
- One AgentProfile has exactly one MaskedProfileRow projection per render.
- One MaskedProfileRow has zero-or-more AuthEnvEntry items and zero-or-more Capability tags.
- One AgentProfile has at most one current ProfileTestOutcome (
testPassed+lastTestedAt). - One AgentProfilesPageData aggregates many MaskedProfileRows with the Org's
ProjectOptionandTaskOptionlists fromwork-management.
Example dialogue
Dev: "Why does
maskProfilederive Capability tags from the name?" Domain expert: "It's a UI hint, not a domain fact — the AgentProfile itself doesn't store capabilities. The list view needs badges, so we infer them from the agent name until a real capability field exists." Dev: "And the AuthEnvEntry values?" Domain expert: "Always masked at the application boundary. RawauthEnvVarsnever leave this module unmasked; the MaskedProfileRow is the only shape the interface layer sees."
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.
- 3d ago First seen · 45 lines · 0 tokens per session scan A a261a9916fd9
CONTEXT is an agent published in the GitHub repository moabualruz/fulcrum (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 638 tokens. 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.
Other agents, from other repositories
pr-manager-lite
Finish GitHub pull requests for tinyhumansai/openhuman when the PR branch is ALREADY checked out locally (e.g. via the preem shell helper) with base merged in and upstream tracking set. Skips fetch/checkout/conflict-resolution; goes straight to collecting reviewer/bot feedback, applying every actionable fix, running…
taskmaster
Development Pipeline Orchestrator who manages entire development workflows by coordinating specialist agents through configurable pipelines for any type of project.
designguru
Expert Design Guidance & Analysis Specialist who provides professional UI/UX insights, design system guidance, and visual recommendations for any type of application.
qualityqueen
Quality Assurance & Code Standards Specialist who ensures code meets project standards across any technology stack. Fixes basic issues and escalates complex problems with detailed analysis.
codecrusher
Senior Developer & Implementation Expert who transforms architectural plans into high-quality, production-ready code across any technology stack.
ship-and-babysit
Commit local changes, push the branch to the user's fork, open or reuse a PR against tinyhumansai/openhuman:main, then babysit CI and CodeRabbit feedback until the PR is green and clean. Use when the user wants an end-to-end ship flow, not just implementation.