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 mgifford/accessibility-skills --skill upstream-firstgit clone --depth 1 https://github.com/mgifford/accessibility-skillsWrote 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/mgifford/accessibility-skills/upstream-first)<a href="https://agentmods.dev/skills/mgifford/accessibility-skills/upstream-first"><img src="https://agentmods.dev/badge/skills/mgifford/accessibility-skills/upstream-first/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mgifford/accessibility-skills/upstream-first"><img src="https://agentmods.dev/badge/skills/mgifford/accessibility-skills/upstream-first.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00093 | $0.01431 |
| Opus 5 | $0.00046 | $0.00715 |
| Sonnet 5 | $0.00019 | $0.00286 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
upstream-first 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 9d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 9d ago First seen · 126 lines · 93 tokens per session scan A ec91d3f7a260
upstream-first is a skill published in the GitHub repository mgifford/accessibility-skills (44 stars, last pushed 1mo ago), licensed AGPL-3.0. It adds 93 tokens to every session and 1,431 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
astro-troubleshooting
This skill should be used when debugging Astro issues, identifying Astro anti-patterns, fixing common Astro mistakes, troubleshooting Astro errors, resolving "document is not defined" in Astro, resolving "window is not defined" in Astro, diagnosing a component not interactive, fixing content validation errors…
fastify-troubleshooting
This skill should be used when debugging Fastify issues, identifying Fastify anti-patterns, diagnosing common Fastify mistakes, performing Fastify error troubleshooting, investigating request.body undefined in hook, fixing decorator shared across requests, resolving hook executing twice, handling reply already sent…
chrome-ext-troubleshooting
This skill should be used when debugging Chrome extension issues, diagnosing Chrome Web Store rejections, or troubleshooting build problems. Trigger when: "extension not working", "CWS rejection", "Chrome Web Store rejected", "Yellow Magnesium", "Purple Potassium", "Blue Argon", "Red Magnesium", "extension build…
check-pipeline
Check that a code and its Pipeline/ .md are still compatible — that every symbol, cell number, data file, and data-flow claim in the pipeline doc still matches the current code (drift detection). Use after editing a documented notebook/engine/script, before trusting a pipeline doc, or on request ("does the pipeline…
reality-check
Re-derive a contested or pushed-back claim in isolation from the definitions, to catch sycophantic capitulation. Use when a result is disputed or you suspect you changed an answer only because the user pushed back.
rudder-destination-debugging
Diagnoses why events are failing, dropping, or not arriving at a destination. Use when events are missing from a destination, seeing high error rates, getting auth failures, or events are stuck retrying.