

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
123456# Global Copilot Instructions78This file is the **thin router** - it tells you what to load and when. It loads every conversation, so it stays small.910---1112## Quality Loop Hard Rule (NON-SKIPPABLE)1314> **HARD RULE**: Before editing, creating, or deleting any file for a code or docs change, run `.agentx/agentx.ps1 loop start -p "<task>"` as your ABSOLUTE FIRST tool call. Reading files and running `loop status` are allowed; mutating the workspace before `loop start` succeeds is a contract violation. The loop is NOT done until `.agentx/agentx.ps1 loop complete -s "<summary>"` succeeds, and at least one history iteration summary must contain the word "review" (subagent review pass). The pre-commit hook blocks commits when these conditions are unmet.15>16> **Minimum 5 iterations**: EVERY agent and task class requires at least 5 quality iterations before `loop complete` is allowed (enforced by the loop CLI, agentic runner, extension runtime, and pre-commit hook). Report each iteration with `loop iterate -s "..."`, then summarize before completing.17>18> **Cross-Cutting Agent Protocol**: The shared rules (quality loop, subagent review, per-iteration reporting, Karpathy, Model Council, Scrub, Brainstorm, Plan, Research) are defined ONCE in [.github/AGENT-PROTOCOL.md](AGENT-PROTOCOL.md). Agent files keep only the front-loaded Pre-edit gate + Honesty rule stubs and point there.19>20> **Honesty rule**: If asked whether the loop ran, run `.agentx/agentx.ps1 loop status` and report the actual state. Do not claim completion unless `loop complete` succeeded in the current session.21>22> Frontmatter-only enforcement is insufficient -- this rule lives here in body prose because models routinely skip rules placed only in deeper docs.2324---2526## Mandatory Workflow Gates (NON-SKIPPABLE)2728These four rules carry the same weight as the Quality Loop. The pre-commit hook hard-fails commits that violate them. Bypass tokens exist for genuine emergencies only.2930> **Compound Capture (Done gate)**: Any commit that stages an APPROVED review under `docs/artifacts/reviews/REVIEW-*.md` MUST also stage the matching `docs/artifacts/learnings/LEARNING-<issue>.md`, OR record a skip rationale in the issue close comment and tag the commit message with `[skip-capture]`. Work is NOT Done until Compound Capture is resolved. See [AGENTS.md#compound-engineering-hard-rule](../AGENTS.md#compound-engineering-hard-rule).31>32> **Model Council (ADR/PRD/Eval gate -- MANDATORY, NO SKIP)**: Any commit that stages a new `docs/artifacts/adr/ADR-*.md` MUST also stage a matching `docs/artifacts/adr/COUNCIL-*.md` capturing 3 diverse-model perspectives and a Synthesis section. Mandatory for Product Manager (prd-scope), Architect (adr-options), and any complex task; also Data Scientist (ai-design), Reviewer (code-review), and Consulting Research. There is no skip token -- the pre-commit hook hard-fails when the COUNCIL file is missing. See [AGENTS.md#role-pipeline-reference](../AGENTS.md#role-pipeline-reference).33>34> **Execution Plan (complex-work gate)**: Any commit changing **8 or more** code files (`.ts/.tsx/.js/.ps1/.py/.cs/.go/.rs/.tf/.bicep/.sql`) MUST stage a corresponding `docs/execution/plans/EXEC-PLAN-*.md` derived from [.github/templates/EXEC-PLAN-TEMPLATE.md](../.github/templates/EXEC-PLAN-TEMPLATE.md), OR tag the commit message with `[skip-plan]`. Plans are living documents and MUST be updated, not only authored. See [docs/WORKFLOW.md#execution-plans-for-complex-work](../docs/WORKFLOW.md#execution-plans-for-complex-work).35>36> **Brainstorm (Engineer pre-Plan gate)**: When acting in the Engineer phase on non-trivial work, the `Research -> Brainstorm -> Plan -> Design -> Implement -> Test -> Review` pipeline is mandatory. The Brainstorm step is satisfied by recording at least one entry of type `brainstorm` in the clarification ledger OR an `## Alternatives Considered` block inside the execution plan **before** Plan is written. This step has no missing-file hook gate; reviewers MUST verify it during the review phase. See [AGENTS.md#pipeline-phase-compliance-hard-rule](../AGENTS.md#pipeline-phase-compliance-hard-rule).3738**Honesty rule**: If asked whether any of these gates ran, inspect the staged files and commit message and report the actual state. Never claim a gate was satisfied without the artifact or skip token.3940---4142## Retrieval-Led Reasoning4344**IMPORTANT**: Prefer retrieval-led reasoning over pre-training-led reasoning for ALL implementation tasks.45Always `read_file` the relevant SKILL.md, instruction file, or spec before generating code.46Do NOT rely on training data for project-specific patterns, conventions, or APIs.47If a skill, spec, or doc exists in the workspace, read it first; generate second.4849---5051## Context Loading Rules5253**Load context on-demand, not upfront.** Match the task to the right documents:5455| Task | Load | Skip |56|------|------|------|57| Writing/editing code in existing files | [AGENTS.md](../AGENTS.md) + Language instruction (auto via `applyTo`) + relevant skills | Skills not matching task |58| Creating new files, features, issues | [AGENTS.md](../AGENTS.md) (workflow + classification) | Skills not matching task |59| Multi-agent coordination, handoffs | [AGENTS.md](../AGENTS.md) + [docs/WORKFLOW.md](../docs/WORKFLOW.md) | Unrelated skills |60| Answering questions, research | Nothing extra - use tools | AGENTS.md, Skills.md |61| Debugging | Language instruction + error handling skill | AGENTS.md |6263**Token budget**: Load only the skills relevant to the task and active phase. Use [Skills.md Quick Reference](../Skills.md) to pick the right ones.6465---6667## When to Read AGENTS.md6869Read [AGENTS.md](../AGENTS.md) for **any coding or workflow task** - it contains classification, commit format, and security checklist. For workflow details, routing, and handoff rules, see [docs/WORKFLOW.md](../docs/WORKFLOW.md).7071> **Skip AGENTS.md** for: answering questions, research, and debugging only.7273---7475## Issue-First Rule7677When AGENTS.md applies (see above), follow the issue-first workflow:781. Create issue **before** starting work (no retroactive issues)792. Update status: `Backlog -> In Progress -> In Review -> Done`803. Reference issue in commits: `type: description (#ID)`8182> **Note**: In Local Mode, issue enforcement is **optional** by default. Toggle with `agentx config set enforceIssues true`.8384---8586## Instruction Files (Auto-Loaded)8788These load automatically when editing matching files - no manual action needed:8990| Instruction | Triggers on |91|-------------|-------------|92| `ai.instructions.md` | `*agent*`, `*llm*`, `*model*`, `*workflow*`, `agents/` |93| `python.instructions.md` | `*.py`, `*.pyx` |94| `csharp.instructions.md` | `*.cs`, `*.csx` |95| `typescript.instructions.md` | `*.ts` (backend/server TypeScript) |96| `react.instructions.md` | `*.tsx`, `*.jsx`, `components/`, `hooks/` |9798For file types not listed above, load the matching **skill** on demand from [Skills.md](../Skills.md):99`*.tf`/`*.tfvars` -> `infrastructure/terraform`, `*.bicep`/`*.bicepparam` -> `infrastructure/bicep`,100`*.razor` -> `languages/blazor`, `*.sql` -> `languages/sql-server` + `languages/postgresql`,101`*.yml`/`*.yaml` -> `operations/yaml-pipelines` + `operations/github-actions-workflows`,102`Controllers/`/`api/` -> `architecture/api-design`, `**/ux/**` -> `design/ux-ui-design`.103104---105106## Session State107108- `manage_todo_list` - Track tasks within current session109- `get_changed_files` - Review uncommitted work before commits110- `get_errors` - Check compilation state after changes111112---113114## Reference115116- **Workflows & Agent Roles**: [AGENTS.md](../AGENTS.md) (map) + [docs/WORKFLOW.md](../docs/WORKFLOW.md) (workflow details)117- **Skills Index**: [Skills.md](../Skills.md) (use Quick Reference to pick skills)118- **Quality & Debt**: [docs/QUALITY_SCORE.md](../docs/QUALITY_SCORE.md) | [docs/tech-debt-tracker.md](../docs/tech-debt-tracker.md)119- **Golden Principles**: [docs/GOLDEN_PRINCIPLES.md](../docs/GOLDEN_PRINCIPLES.md)120- **Frontmatter Validation**: `pwsh scripts/validate-frontmatter.ps1`121122## ASCII-Only Rule123124All source code, scripts, configuration files, and documentation in this repository **MUST** use ASCII characters only (U+0000-U+007F). This applies to all `.ps1`, `.sh`, `.py`, `.ts`, `.js`, `.yml`, `.yaml`, `.json`, and `.md` files.125126- **MUST NOT** use emoji, Unicode symbols, box-drawing characters, or any non-ASCII characters127- **MUST** use ASCII equivalents: `[PASS]` not check marks, `[FAIL]` not cross marks, `[WARN]` not warning symbols, `->` not arrows, `+=-|` not box-drawing, `"` not smart quotes128- **MUST** use plain ASCII dashes (`-`) instead of em-dashes or en-dashes129- **MUST** use `[1]`, `[2]`, `[3]` instead of circled numbers130131This ensures cross-platform compatibility and prevents encoding issues in terminals, CI/CD pipelines, and editors.132133---134135## Directive Language (RFC 2119)136137All instruction files use RFC 2119 keywords:138- **MUST** / **MUST NOT** - Absolute requirement or prohibition139- **SHOULD** / **SHOULD NOT** - Strong recommendation (exceptions need justification)140- **MAY** - Truly optional, at developer discretion141
One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| jnPiyush/AgentX.cursor/rules/000-agentx-core.mdc · 14 | Cursor rules | styleapido-notagent-behaviour | 55/100 | 14 days ago | |
| jnPiyush/AgentX.cursor/rules/ai.mdc · 14 | Cursor rules | no sections | 16/100 | 14 days ago | |
| jnPiyush/AgentX.cursor/rules/csharp.mdc · 14 | Cursor rules | no sections | 16/100 | 14 days ago | |
| jnPiyush/AgentX.cursor/rules/python.mdc · 14 | Cursor rules | testlint-format | 32/100 | 14 days ago | |
| jnPiyush/AgentX.cursor/rules/react.mdc · 14 | Cursor rules | no sections | 16/100 | 14 days ago | |
| jnPiyush/AgentX.github/instructions/ai.instructions.md · 14 | Copilot instructions | testing-strategydo-notagent-behaviour | 50/100 | 14 days ago | |
| jnPiyush/AgentX.github/instructions/csharp.instructions.md · 14 | Copilot instructions | teststylesecuritydo-not+1 | 59/100 | 14 days ago | |
| jnPiyush/AgentX.github/instructions/memory.instructions.md · 14 | Copilot instructions | lint-formatperformance | 54/100 | 14 days ago | |
| jnPiyush/AgentX.github/instructions/python.instructions.md · 14 | Copilot instructions | testlint-formatsecuritydo-not+1 | 67/100 | 14 days ago | |
| jnPiyush/AgentX.github/instructions/react.instructions.md · 14 | Copilot instructions | testtypessecuritydo-not+1 | 63/100 | 14 days ago | |
| jnPiyush/AgentX.github/instructions/typescript.instructions.md · 14 | Copilot instructions | setuptestlint-formatstyle+5 | 92/100 | 14 days ago | |
| jnPiyush/AgentXAGENTS.md · 14 | AGENTS.md | lint-formatstylegitsecurity+2 | 69/100 | 14 days ago | |
| jnPiyush/AgentXCLAUDE.md · 14 | CLAUDE.md | lint-formatstylegitsecurity+2 | 81/100 | 14 days ago | |
| jnPiyush/AgentXvscode-extension/.github/AGENTS.md · 14 | AGENTS.md | lint-formatstylegitsecurity+2 | 69/100 | 14 days ago | |
| jnPiyush/AgentX.cursor/rules/typescript.mdc · 14 | Cursor rules | types | 16/100 | 14 days ago | |
| jnPiyush/AgentX.github/instructions/project-conventions.instructions.md · 14 | Copilot instructions | styledo-not | 50/100 | 11 days ago |
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| chihebnabil/lovable-boilerplate.github/instructions/global.instructions.md · 65 | Copilot instructions | buildlint-formatstylearch+4 | 100/100 | 14 days ago | |
| louislam/uptime-kuma.github/copilot-instructions.md · 90k | Copilot instructions | setupbuildtestlint-format+9 | 100/100 | 14 days ago | |
| HerringtonDarkholme/megarepo.github/copilot-instructions.md · 17 | Copilot instructions | setupbuildtestlint-format+7 | 100/100 | 14 days ago | |
| bagisto/bagisto.github/copilot-instructions.md · 28k | Copilot instructions | setupbuildteststyle+5 | 97/100 | 14 days ago | |
| JCodesMore/ai-website-cloner-template.github/copilot-instructions.md · 32k | Copilot instructions | buildlint-formatstylearch+3 | 97/100 | 7 days ago | |
| nerolis-lab/nerolis-lab.github/copilot-instructions.md · 32 | Copilot instructions | setupbuildtestlint-format+11 | 96/100 | 14 days ago | |
| darkmatter/nixmac.github/copilot-instructions.md · 25 | Copilot instructions | setupbuildtestlint-format+8 | 96/100 | 14 days ago | |
| thangaram611/second-brain.github/copilot-instructions.md · 0 | Copilot instructions | setupteststylearch+4 | 96/100 | 14 days ago |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/jnpiyush-agentx-github-copilot-instructions)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.