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/thavarshan/filterable/copilot-instructionsgit clone --depth 1 https://github.com/Thavarshan/filterableWhat 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 | $0.00456 | $0.00456 |
| Opus 5 | $0.00228 | $0.00228 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
filterable 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 2d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Coding Guidelines
Domain Context
- This package centres on the abstract
Filterclass insrc/Filterable/Filter.php, extended by application-specific filters that receive anIlluminate\Http\Request. - Optional behaviour (validation, caching, logging, rate limiting, memory optimisation, etc.) is implemented via traits in
src/Filterable/Concerns/; Copilot-generated code must compose with these traits instead of duplicating logic. - Eloquent models opt into filtering by using
Filterable\Traits\Filterable; Artesian generator stubs live insrc/Filterable/Console/stubs/.
Coding Rules
- Follow PSR-12: four-space indentation, trailing commas in multi-line arrays, strict type hints, and ordered imports.
- Prefer fluent APIs and immutable-looking helpers; expose feature toggles via
$this->enableFeature()rather than bespoke flags. - When adding new filter methods, camelCase the method name to match the request key (
status→status()), or map via$filterMethodMap. - Respect existing caches and logging patterns by reusing helpers (
buildCacheKey(),logInfo()); do not access the logger or cache container directly. - Keep public APIs typed and documented; add succinct docblocks if behaviour is non-obvious (e.g. transforms, rate limits).
Testing Expectations
- Every new concern or feature flag should be covered by PHPUnit tests under
tests/, using Orchestra Testbench. - Mock collaborators (cache, logger, rate limiter) with Mockery, and assert on state using
getDebugInfo()or dedicated getters. - Provide happy-path, edge, and failure tests—mirror patterns from existing concern tests like
CachingTest.phporHandlesRateLimitingTest.php.
Anti-Patterns to Avoid
- Do not re-run
apply()on the same filter without callingreset(). - Avoid duplicating concern logic directly inside filters; extend or compose existing traits instead.
- Do not introduce framework-specific globals (
request(),auth()) inside reusable traits—inject dependencies through the constructor or method parameters. - Refrain from adding commands or scripts outside the
bin/directory or Composer scripts without project-owner approval.
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.
- 2d ago First seen · 25 lines · 456 tokens per session scan A 46508736a111
filterable copilot-instructions.md is an instructions file published in the GitHub repository Thavarshan/filterable (195 stars, last pushed 2mo ago), licensed MIT. It adds 456 tokens to every session, about $0.0023 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
ULogViewer AGENTS.md
Instructions for carina-studio/ULogViewer, covering agents.md, coding style, naming, formatting & structure and fields & properties.
Weavero CLAUDE.md
Claude Code instructions for mjthoraval/Weavero, covering weavero — guidance for ai coding agents, commands, layout, verify, don't guess and hard invariants (each paid for with a real regression).
Weavero AGENTS.md
AGENTS.md instructions for mjthoraval/Weavero: See CLAUDE.md — it is agent-agnostic despite the name (the convention Zotero's own repos use). Workflows live in .claude/skills/, conventions in .claude/rules/, and the design of the whole setup is explained in .claude/README.md.
ULogViewer CLAUDE.md
Instructions for carina-studio/ULogViewer, a project described as: Cross-Platform, Agent-Native Universal Log Viewer.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.