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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/projectsidewalk/sidewalkwebpage/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/projectsidewalk/sidewalkwebpage/copilot-instructions.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 | $0.00496 | $0.00496 |
| Opus 5 | $0.00248 | $0.00248 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
SidewalkWebpage copilot-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 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.
What it actually says
Project Sidewalk — Copilot review guidance
Crowdsourced sidewalk-accessibility mapping. Backend: Scala 2.13 + Play 3.0, Slick over Postgres/PostGIS. Frontend: vanilla JS (Grunt concat, no transpile), Twirl views. Schema via Play evolutions. Two i18n systems.
Don't duplicate the linters
Formatting and mechanical style are enforced by blocking CI gates: scalafmt, ESLint, Stylelint, HTMLHint, locale key-parity. Do NOT spend review comments on formatting, whitespace, quote style, semicolons, import order, or line length. Focus on correctness, domain rules, and the conventions in the path-scoped files.
Cross-cutting rules to flag
- Backend is the source of truth. Flag hardcoded frontend literals that mirror
backend domain values: label colors/icons, enum members, value ranges (min/max),
thresholds, and especially mappings between them. Colors must come from
util.misc.getLabelColors(labelType); other domain values from a/v3/api/...endpoint or a controller-injected view binding — never re-declared as a JS constant. Note: severity's good/ok/bad meaning is NOT fixed (positive vs negative features invert it), so flag any{1:'good',2:'ok',3:'bad'}-style literal. - Comments say WHY, not WHAT. Flag comments that restate the code, and changelog/narration comments that only make sense against the diff. Tell-tale words: "used to", "previously", "formerly", "replaces the old", "renamed to/from", "no longer". Flag TODO/FIXME with no linked issue.
- i18n: user-facing text changes need translations in all supported languages
(en, es, nl, zh-TW, de, pt-BR, en-US, en-NZ). See i18n instructions. EXCEPTION:
admin-only pages/routes (
app/views/admin/**,/admin/*) ship English-only — do not flag missing translations there. - Accessibility: new/changed UI must meet WCAG 2.1/2.2 AA — flag missing alt text, unlabeled controls, non-token colors with poor contrast, keyboard traps.
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 · 31 lines · 496 tokens per session scan A 41f7b6ec2f54
SidewalkWebpage copilot-instructions.md is an instructions file published in the GitHub repository ProjectSidewalk/SidewalkWebpage (104 stars, last pushed 4d ago), licensed MIT. It adds 496 tokens to every session, about $0.0025 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
expense-budget-tracker AGENTS.md
Instructions for kirill-markin/expense-budget-tracker, covering expense-budget-tracker, rules, components, supported clients and key paths.
postgres-skills AGENTS.md
Instructions for neondatabase/postgres-skills, covering agents.md, repository overview, creating a new skill, directory structure and naming conventions.
pg_exporter AGENTS.md
Instructions for nbari/pg_exporter, covering agents.md, project shape, first steps, devpod workflow (preferred) and local commands.
counterpoise-ledger CLAUDE.md
Instructions for jeffjjohnston/counterpoise-ledger, covering claude.md, project overview, development commands, essential commands and testing.
database-mcp CLAUDE.md
Instructions for hadi21k/database-mcp, covering claude.md, project overview, commands, architecture and layers.
mcp-database CLAUDE.md
Claude Code instructions for DiegoBulhoes/mcp-database, covering claude.md, commands, architecture, invariants (do not weaken) and adding or changing a tool.