AGENTS.full

AGENTS.full is an agent for coding agents from jeremylongworth-source/AgentSkills. It costs 0 tokens per session (1,642 once invoked), scanned A, original, MIT.

A top-level routing guide that tells an agent which local skill to use for different kinds of product, development, planning, evaluation, security, and operations work.

In plain words
What is it for?
Use it to select skills for feature planning, project onboarding, skill evaluation, prompt testing, security reviews, data protection, script permissions, supply-chain risks, and secrets handling.
Why use it?
It helps agents choose focused instructions for a task instead of using an unsuitable or overly broad set of rules. It also defines routes for testing skills and reviewing their risks.

Agent

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 agents/jeremylongworth-source/agentskills/agents.full
Clone the repo
git clone --depth 1 https://github.com/jeremylongworth-source/AgentSkills

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 AGENTS.full

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongworth-source/agentskills/agents.full.svg)](https://agentmods.dev/agents/jeremylongworth-source/agentskills/agents.full)
Your own site
<a href="https://agentmods.dev/agents/jeremylongworth-source/agentskills/agents.full"><img src="https://agentmods.dev/badge/agents/jeremylongworth-source/agentskills/agents.full.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,642 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 5.1 $0.00000 $0.01642
Opus 5 $0.00000 $0.00821
Sonnet 5 $0.00000 $0.00328
Haiku 4.5 $0.00000 $0.00164

Measured 5d ago against content hash d4565241e29d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

AGENTS.full 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 5d 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.

agents/AGENTS.full.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use local skills as the primary routing layer for domain work.

For broad or ambiguous feature/product requests, use product-brainstorming-planning before implementation planning.

Use skill-evaluation-iteration when testing, comparing, strengthening, or forward-testing skills.

Use agentskills-project-onboarding when setting up AgentSkills in a new or existing repository, choosing a focused skillset or atomic skills, planning project agent instructions, deciding project versus user scope, recommending MCP presets, or verifying that AgentSkills routes correctly without installing unnecessary broad bundles.

Use skill-benchmark-design, scenario-test-authoring, before-after-evaluation, acceptance-criteria-mapper, prompt-regression-testing, skill-output-scoring, and skill-token-overhead-review for AgentOps evaluation, route scenarios, before/after reports, prompt regression tests, scoring, measured context overhead review, repeated-run compounding checks, and split/merge/compose decisions.

Use skill-threat-model, prompt-injection-review, data-exfiltration-review, script-permission-review, supply-chain-review, secrets-handling-review, and safe-install-checklist when auditing agent skills before install or publish.

Use readme-upgrade, api-doc-writing, release-notes, changelog-maintenance, architecture-docs, migration-guide, developer-onboarding, and tutorial-writing for technical documentation workflows.

Use api-contract-design, database-schema-review, auth-flow-design, service-boundary-design, error-handling-contracts, rate-limit-design, and backend-test-plan for backend API contracts, schemas, auth flows, service boundaries, error contracts, rate limits, and backend verification.

Use deployment-plan, ci-workflow-plan, containerization-plan, environment-config-review, rollback-plan, cloud-cost-review, and production-readiness-review for DevOps, cloud, and release planning.

Use unit-test-generation, integration-test-plan, e2e-test-plan, bug-reproduction, qa-matrix, accessibility-test-plan, and performance-test-plan for quality and testing workflows.

Use metric-definition, dashboard-design, cohort-analysis, funnel-analysis, retention-analysis, sql-analysis-plan, experiment-readout, and analytics-instrumentation-plan for data analytics and BI workflows.

Use content-pillars, short-form-hooks, video-script, ai-video-prompt-pack, thumbnail-title-brief, social-asset-production, caption-writer, content-calendar, longform-to-shorts, newsletter-repurpose, podcast-outline, owned-social-profile-audit, brand-social-launch-pack, and publishing-checklist for creator content engines, hooks, scripts, AI video prompt packs, social visuals, calendars, profile audits, launch packs, captions, repurposing, and pre-publish checks.

Use brand-pitch, media-kit-builder, sponsorship-package, rate-card-builder, campaign-proposal, usage-rights-checklist, deal-negotiation-prep, deliverables-tracker, campaign-recap, and renewal-pitch for creator sponsorship workflows, media kits, rate cards, campaign proposals, rights review, negotiation prep, recaps, and renewals.

Use creator-content-performance-review and affiliate-performance-report with existing dashboard, metric, retention, cohort, funnel, experiment, attribution, and instrumentation skills for creator analytics reporting, sponsor reports, content performance, audience growth, affiliate reporting, content experiments, and dashboard specs.

Use creator-offer-ladder and creator-owned-product-launch-plan with existing pricing, margin, affiliate, dashboard, owner, content, publishing, and experiment skills for creator monetization, owned-product launches, pricing reviews, memberships, paid communities, merch, affiliate review, and monetization dashboards.

Use creator-invoice-readiness and creator-production-ops-brief with existing owner, cash-flow, finance close, pipeline, deliverables, bottleneck, vendor, action, documentation, rights, and metric skills for creator business operations, weekly ops dashboards, sponsor pipeline hygiene, invoice readiness, production handoffs, asset checklists, and contractor/assistant briefs.

Read the full file on GitHub · 141 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. 5d ago First seen · 141 lines · 0 tokens per session scan A d4565241e29d

Subscribe to this mod's changes

AGENTS.full is an agent published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,642 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.