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 instructions/projectsidewalk/sidewalkwebpage/frontend-jsgit clone --depth 1 https://github.com/ProjectSidewalk/SidewalkWebpageWrote 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/instructions/projectsidewalk/sidewalkwebpage/frontend-js)<a href="https://agentmods.dev/instructions/projectsidewalk/sidewalkwebpage/frontend-js"><img src="https://agentmods.dev/badge/instructions/projectsidewalk/sidewalkwebpage/frontend-js.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 | $0.00447 | $0.00447 |
| Opus 5 | $0.00224 | $0.00224 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
SidewalkWebpage frontend-js.instructions.md 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 today.
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.
What it actually says
Frontend JS review (ES2022 target)
- Flag
var(use const/let), string+concatenation for HTML (use template literals), and jQuery AJAX where nativefetch+ Promises fit. Prefer arrow functions in callbacks to keepthisbound. - The constructor-function pattern (
function Foo(){ const self=this; ...; return self }) should be aclasswith#privatefields. Flag new code using it. - No hardcoded domain values (see repo-wide rule): use
util.misc.getLabelColors(labelType)andutil.misc.getIconImagePaths(labelType); source enum members, ranges, and mappings from/v3/api/...or a view binding. Flag any{1:'good',2:'ok',3:'bad'}-style severity map, and anylabel_type_icons/*.pngpath — the frontend uses the scalable_small.svgmarker only. - No hardcoded
/assets/...URLs. Name the asset by its logical path underpublic/and resolve it withutil.assetPath('images/icons/openhand.cur'), so staged builds serve the content-fingerprinted, year-cached copy. Build the whole path before resolving a dynamic one; never concatenate onto a resolved URL or keep a base directory, which can't be fingerprinted.make lint-asset-pathsenforces this. - Tool UI scaling: in Explore, Validate, and overlays layered over them, every
fixed px dimension set from JS must be
calc(<n>px * var(--ui-scale, 1)). Flag bare px. (Fixed page chrome like the navbar is exempt.) - JSDoc on every class and non-trivial method (including
#private); use@returns(not@return) with a{Type}. - Prefer
data-i18n="ns:key"over hardcoded English strings in generated HTML.
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.
- today Changed · +6 lines · +104 tokens per session 03e6273efe04
- 4d ago First seen · 22 lines · 343 tokens per session scan A 047a9128a69e
SidewalkWebpage frontend-js.instructions.md is an instructions file published in the GitHub repository ProjectSidewalk/SidewalkWebpage (105 stars, last pushed today), licensed MIT. It adds 447 tokens to every session, about $0.0022 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 instructions, from other repositories
osm-tagging-schema-mcp CLAUDE.md
Claude Code instructions for gander-tools/osm-tagging-schema-mcp, covering project: openstreetmap tagging schema mcp server, project overview, purpose, core functionality and complete tool set (9 tools).
starwind-ui AGENTS.md
Instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
Codex-Skills AGENTS.md
AGENTS.md instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.
ACCESSIBILITY.md AGENTS.md
AGENTS.md instructions for mgifford/ACCESSIBILITY.md, covering repository instructions for ai coding agents, scope, when each instruction file is useful, project mission and status and required project context.
barkeep AGENTS.md
AGENTS.md instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.
OpenGUI CLAUDE.md
Claude Code instructions for Core-Mate/OpenGUI, covering opengui release - repository guide for claude code / codex, 1. repository positioning, 2. default working rules, 3. high-level architecture and 4. directory map.