atris 1.0.0

package/.claude/settings.local.json

@@ -0,0 +1,11 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(chmod:*)",
+      "Bash(npm link)",
+      "Bash(atris:*)"
+    ],
+    "deny": [],
+    "ask": []
+  }
+}

package/README.md

@@ -0,0 +1,3 @@
+# ATRIS
+
+Drop `atris.md` into any codebase and have your favorite coding agent (Claude Code, OpenAI Codex, etc.) read it to scaffold a fully-instrumented, AI-navigable system in under 10 minutes. The agent will generate CODE_MAP.md, three specialized agent specs, and TASK_CONTEXTS.md—transforming your project into a self-documenting workspace with exact file:line references for every feature.

package/atris.md

@@ -0,0 +1,270 @@
+# atris.md — Universal Codebase Instrumentation Blueprint
+
+> **One markdown file. Drop it anywhere. Agents scaffold a fully-instrumented codebase in <10 minutes.**
+
+This spec defines how to transform any codebase into a self-documenting, AI-navigable system. Five artifacts (CODE_MAP.md, 3 agent specs, TASK_CONTEXTS.md) + autonomous agents = 10x faster collaboration.
+
+**See [`ATRIS_NOTES.md`](./ATRIS_NOTES.md) for vision, roadmap, and future phases (sync, sessions, agent crews).**
+
+---
+
+## Phase 1: Generate CODE_MAP.md (Exact File Context)
+
+**Goal:** Create a single-source-of-truth navigation guide that agents reference for all architecture questions.
+
+**Why This Matters:**
+- Agents waste time re-learning codebase structure on each task
+- CODE_MAP.md eliminates friction—one grep-friendly index that's always accurate
+- All agents reference the same truth, preventing contradictory guidance
+
+**Agent Instructions:**
+
+1. **Scan the project root** (ignore: `node_modules/`, `.git/`, `dist/`, `build/`, `.DS_Store`, `*.log`)
+
+2. **For each major directory** (depth 1-2 levels), extract:
+   - Purpose (1 sentence: why does this directory exist?)
+   - Key files with line-count ranges (e.g., `auth.ts: 200 lines`)
+   - Search accelerators (ripgrep patterns for fast navigation)
+
+3. **Create `/CODE_MAP.md`** with these sections:
+   - **Quick Reference Index** (top) — Grep-friendly shortcuts (e.g., `CHAT:BACKEND -> rg -n "def quick_chat" backend/`)
+   - **By-Feature** — Chat, files, auth, billing, etc. (answer: "where is feature X?")
+   - **By-Concern** — State management, API layer, UI system, etc. (answer: "where is concern Y?")
+   - **Critical Files** — Files >10KB or >100 lines of logic = high-impact (mark as ⭐)
+   - **Entry Points** — 3-5 entry points clearly marked (landing page, dashboard, API routes, etc.)
+
+4. **Quality Checklist Before Outputting:**
+   - [ ] Can I run `rg -l "TODO|FIXME"` and navigate to each via line numbers in CODE_MAP?
+   - [ ] Does every major file have a one-liner explaining its purpose?
+   - [ ] Are there 10+ ripgrep patterns I can use to navigate quickly?
+   - [ ] Can a new developer answer "where is X?" in <30 seconds using this map?
+
+5. **Output:** `/CODE_MAP.md` (target: 500-800 lines for large codebases; scale to project size)
+
+---
+
+## Phase 2: Spawn 3 Foundation Agents
+
+After CODE_MAP.md exists, generate agent specs from CODE_MAP insights. Each agent has explicit guardrails.
+
+### Agent 1: **@codebase_AGENT.md**
+
+- **Role:** Codebase Navigator & Architecture Expert
+- **Activation Prompt:**
+  ```
+  You are the codebase expert. Your sole job is answering "where is X?" with precision.
+
+  Rules:
+  1. ALWAYS start with: "According to CODE_MAP.md, [item] is located in..."
+  2. ALWAYS cite file:line references (e.g., `app/auth/middleware.ts:15-45`)
+  3. Explain data flows end-to-end (frontend → backend → database)
+  4. Identify coupling points and architecture violations
+  5. Guide developers to the right file in <5 clicks
+
+  DO NOT:
+  - Execute code changes or file modifications
+  - Make architecture decisions without explicit approval
+  - Assume file locations; always reference CODE_MAP.md
+  ```
+
+- **Knowledge Base:** CODE_MAP.md, architecture docs, API specs, system design docs
+- **Success Metric:** Every question answered with exact file:line references, zero guesses
+
+### Agent 2: **@task_AGENT.md**
+
+- **Role:** Context-Aware Task Executor
+- **Activation Prompt:**
+  ```
+  You are the task executor. When given a task, extract exact context and execute step-by-step.
+
+  Rules:
+  1. Read CODE_MAP.md first; extract file:line references for all related files
+  2. Identify ALL files that will be touched (use ripgrep patterns from CODE_MAP)
+  3. Map dependencies and risk zones
+  4. Create a concise 4-5 sentence execution plan with:
+     - File paths
+     - Line numbers for modifications
+     - Exact description of changes
+  5. Execute step-by-step, validating at each stage
+
+  Format: "Task: [name] | Files: [path:line] | Changes: [exact description]"
+
+  DO NOT:
+  - Skip validation steps
+  - Modify files outside the planned scope
+  - Ignore type errors or test failures
+  ```
+
+- **Knowledge Base:** CODE_MAP.md, TASK_CONTEXTS.md (generated), test suite, type definitions
+- **Success Metric:** Tasks completed 95% first-try with zero regressions
+
+### Agent 3: **@validator_AGENT.md**
+
+- **Role:** Quality Gatekeeper & Architecture Guardian
+- **Activation Prompt:**
+  ```
+  You are the validator. After ANY change, verify safety and accuracy.
+
+  Rules:
+  1. Run type-check, lint, tests automatically
+  2. Verify all file references in CODE_MAP.md still exist and are accurate
+  3. Update CODE_MAP.md if architecture changed
+  4. Check for breaking changes or coupling violations
+  5. Report: "✓ Safe to merge" or "⚠ Risks: [list]"
+
+  ALWAYS cite CODE_MAP.md and explain why changes are safe/risky.
+
+  DO NOT:
+  - Approve changes without running tests
+  - Allow breaking changes silently
+  - Update CODE_MAP.md without explaining what changed
+  ```
+
+- **Knowledge Base:** CODE_MAP.md, test suite, type definitions, architecture principles
+- **Success Metric:** Zero undetected breaking changes reach production
+
+---
+
+## Phase 3: Task Context System (TASK_CONTEXTS.md)
+
+**Goal:** Automatic task extraction with exact file context, so agents never guess.
+
+**Generated File Format:**
+
+```markdown
+# Task Contexts — Auto-extracted from CODE_MAP.md
+
+## Task Template
+- **Task ID:** T-[AUTO]
+- **Name:** [Feature/Fix Name]
+- **Context Files:** [file:line_start-line_end] (from CODE_MAP critical files)
+- **Execution Plan:**
+  1. [Step 1 with file:line reference]
+  2. [Step 2 with file:line reference]
+  3. [Step 3 with file:line reference]
+- **Success Criteria:** [Measurable, testable]
+- **Dependencies:** [Task IDs or external dependencies]
+- **Risk Level:** [Low/Medium/High + reasoning]
+
+## Example Task (Auto-Generated)
+- **Task ID:** T-001
+- **Name:** Add authentication to file upload
+- **Context Files:**
+  - `app/api/files/upload/route.ts:1-50` (handler)
+  - `app/auth/middleware.ts:15-45` (auth check)
+  - `types/auth.ts:8-20` (auth types)
+- **Execution Plan:**
+  1. Add `verifySession()` call to upload handler (line 20)
+  2. Return 401 if no session (add lines 21-23)
+  3. Add auth test to `__tests__/upload.test.ts:112-125`
+  4. Run `npm run test` and verify all pass
+- **Success Criteria:** Upload rejects unauthenticated requests; all tests pass; CODE_MAP.md updated
+- **Dependencies:** None
+- **Risk Level:** Low (isolated auth check, no cross-module impact)
+```
+
+**Agent Instructions:**
+
+1. After CODE_MAP.md is generated, scan for:
+   - Incomplete features (TODOs, FIXMEs, marked with line numbers)
+   - High-risk files (>500 lines, multiple imports, touching shared state)
+   - Cross-module dependencies that could break easily
+
+2. Auto-generate 5-10 canonical tasks with exact file:line references
+   - Include both quick wins (low-risk) and strategic work (high-impact)
+   - Map all dependencies explicitly
+
+3. Output: `/TASK_CONTEXTS.md` (maintains and evolves as project changes)
+
+4. On each CODE_MAP.md update, regenerate TASK_CONTEXTS.md to reflect new state
+
+---
+
+## Phase 4: Activation & Handoff
+
+**When All Five Required Artifacts Exist:**
+
+- ✅ `CODE_MAP.md` (navigation guide)
+- ✅ `@codebase_AGENT.md` (question answerer)
+- ✅ `@task_AGENT.md` (executor)
+- ✅ `@validator_AGENT.md` (gatekeeper)
+- ✅ `TASK_CONTEXTS.md` (task bank)
+
+**Agent Behavior Activates Automatically:**
+
+| Trigger | Agent | Action |
+|---------|-------|--------|
+| "Where is X?" | @codebase_AGENT | Answers with CODE_MAP.md:line reference |
+| "Do task Y" | @task_AGENT | Extracts context, plans execution, cites file:line |
+| After change | @validator_AGENT | Checks validity, updates docs, blocks unsafe changes |
+| New agent joins | @codebase_AGENT | Reads CODE_MAP.md, immediately productive (no ramp-up) |
+
+**Validation Checklist:**
+
+- [ ] All three agents can read and cite CODE_MAP.md
+- [ ] @codebase_AGENT answers 5 test questions with file:line accuracy
+- [ ] @task_AGENT completes a sample task without regressions
+- [ ] @validator_AGENT successfully detects and blocks a breaking change
+- [ ] CODE_MAP.md is accurate and stays in sync with code
+
+---
+
+## Phase 5: Future Roadmap (Vision)
+
+**See [`ATRIS_NOTES.md`](./ATRIS_NOTES.md) for full roadmap. Preview:**
+
+- **Phase 5a: Sync** — Local + cloud markdown sync, enabling offline editing and asynchronous agent work
+- **Phase 5b: Sessions** — Step-by-step markdown workflows with `!status`, `!result` tags for interactive collaboration
+- **Phase 5c: Crew Orchestration** — Multi-agent coordination (codebase expert → executor → validator) from markdown config
+
+---
+
+## Why This Works
+
+1. **CODE_MAP = Single Source of Truth** — All agents reference one navigation guide; no contradictions
+2. **Exact File:Line Context** — No guessing; every answer is pinpoint accurate
+3. **Self-Validating** — @validator_AGENT keeps CODE_MAP and artifacts fresh automatically
+4. **Scalable to Any Codebase** — Works for monorepos, microservices, solo projects, legacy systems
+5. **Agent Handoff** — New agent joins, reads CODE_MAP, immediately productive (no ramp-up time)
+6. **Offline + Async Ready** — Markdown files work offline; sync on schedule (future Phase 5a)
+
+---
+
+## Implementation Checklist
+
+- [ ] **Phase 1:** Generate CODE_MAP.md on fresh codebase (10 min)
+- [ ] **Phase 1 Validation:** Run ripgrep shortcuts from CODE_MAP; all work (5 min)
+- [ ] **Phase 2:** Spawn 3 agent specs with activation prompts (5 min)
+- [ ] **Phase 3:** Auto-generate TASK_CONTEXTS.md from CODE_MAP insights (10 min)
+- [ ] **Phase 4:** Test system (ask @codebase_AGENT a question, watch it cite CODE_MAP:line) (10 min)
+- [ ] **Ongoing:** Each CODE_MAP update triggers TASK_CONTEXTS refresh
+
+**Total time to full instrumentation: ~40 minutes**
+
+---
+
+## Quick Start
+
+```bash
+# 1. Copy atris.md to your project root
+cp atris.md /path/to/your/project/
+
+# 2. Hand atris.md to any agent with this prompt:
+# "Read atris.md. Execute Phase 1-4 to scaffold this codebase."
+
+# 3. Agent generates 5 artifacts
+# 4. Your codebase is now fully instrumented for AI collaboration
+
+# Future: atris-cli automates this
+# atris init
+```
+
+---
+
+**Status:** Spec finalized. When deployed to a fresh project, agents will:
+1. Map the codebase in <10 minutes
+2. Answer questions with file:line precision
+3. Execute tasks with full context
+4. Maintain docs as code evolves
+
+*Drop atris.md anywhere. Agents follow the blueprint. Codebase becomes fully instrumented for AI collaboration.*

package/bin/atris.js

@@ -0,0 +1,49 @@
+#!/usr/bin/env node
+
+const fs = require('fs');
+const path = require('path');
+
+const command = process.argv[2];
+
+if (!command) {
+  console.log('Usage: atris <command>');
+  console.log('Commands:');
+  console.log('  init   - Initialize ATRIS in current project');
+  process.exit(0);
+}
+
+// Command handlers
+if (command === 'init') {
+  initAtris();
+} else {
+  console.log(`Unknown command: ${command}`);
+  console.log('Run "atris" without arguments to see available commands');
+  process.exit(1);
+}
+
+function initAtris() {
+  const targetDir = path.join(process.cwd(), 'atris');
+  const sourceFile = path.join(__dirname, '..', 'atris.md');
+  const targetFile = path.join(targetDir, 'atris.md');
+
+  // Create atris/ folder if it doesn't exist
+  if (!fs.existsSync(targetDir)) {
+    fs.mkdirSync(targetDir, { recursive: true });
+    console.log('✓ Created atris/ folder');
+  } else {
+    console.log('✓ atris/ folder already exists');
+  }
+
+  // Copy atris.md to the folder
+  if (fs.existsSync(sourceFile)) {
+    fs.copyFileSync(sourceFile, targetFile);
+    console.log('✓ Copied atris.md to atris/ folder');
+    console.log('\nATRIS initialized! Next steps:');
+    console.log('1. Read atris/atris.md for instructions');
+    console.log('2. Paste the content to Claude or your favorite AI agent');
+    console.log('3. The agent will generate CODE_MAP.md and specialized agents');
+  } else {
+    console.error('✗ Error: atris.md not found in package');
+    process.exit(1);
+  }
+}

package/high_output_agent_management_v1.pdf

@@ -0,0 +1,112 @@
+%PDF-1.4
+%���� ReportLab Generated PDF document http://www.reportlab.com
+1 0 obj
+<<
+/F1 2 0 R /F2 3 0 R
+>>
+endobj
+2 0 obj
+<<
+/BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font
+>>
+endobj
+3 0 obj
+<<
+/BaseFont /Helvetica-Bold /Encoding /WinAnsiEncoding /Name /F2 /Subtype /Type1 /Type /Font
+>>
+endobj
+4 0 obj
+<<
+/Contents 10 0 R /MediaBox [ 0 0 612 792 ] /Parent 9 0 R /Resources <<
+/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
+>> /Rotate 0 /Trans <<
+
+>> 
+  /Type /Page
+>>
+endobj
+5 0 obj
+<<
+/Contents 11 0 R /MediaBox [ 0 0 612 792 ] /Parent 9 0 R /Resources <<
+/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
+>> /Rotate 0 /Trans <<
+
+>> 
+  /Type /Page
+>>
+endobj
+6 0 obj
+<<
+/Contents 12 0 R /MediaBox [ 0 0 612 792 ] /Parent 9 0 R /Resources <<
+/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
+>> /Rotate 0 /Trans <<
+
+>> 
+  /Type /Page
+>>
+endobj
+7 0 obj
+<<
+/PageMode /UseNone /Pages 9 0 R /Type /Catalog
+>>
+endobj
+8 0 obj
+<<
+/Author (\(anonymous\)) /CreationDate (D:20251016232521+00'00') /Creator (\(unspecified\)) /Keywords () /ModDate (D:20251016232521+00'00') /Producer (ReportLab PDF Library - www.reportlab.com) 
+  /Subject (\(unspecified\)) /Title (\(anonymous\)) /Trapped /False
+>>
+endobj
+9 0 obj
+<<
+/Count 3 /Kids [ 4 0 R 5 0 R 6 0 R ] /Type /Pages
+>>
+endobj
+10 0 obj
+<<
+/Filter [ /ASCII85Decode /FlateDecode ] /Length 1270
+>>
+stream
+Gat=*?#Sa]&:Dg-fXIZ1UU+K:5458g'l!,e*dU86/,De0/"6i6.O5b$qs-=:g!7VaG%'#oCg,?6m*#s)dho8NrN07tO&LB!>>BH0dt[EK.r"hb>u-OLO7Mt/k8/5`=l<bjNRO>g+(8Bf^!eDg\%#-u74G\p$Fr`WR8"%d3j%Z-PFaGkcTZN#UoQN187.T]F)L+".=KBhU?O7(J#:[B]7Alo]Ug>sa++FH0A"7`Yl5EXEW\$l&G$9\GbR"jlM3a;o%dpt^"^>IXn;M^E`4/4BR%:nnp[NhIcdWP=fO5_0J1h4QMBY@*U,i>6J8oXF)"[1lm^r+r9d]*r@_eFJP=(1JJ@p\8H.a]cX^.'/&e9Y2X*K\7Q*_'RS(9oPH)_^FPDRA*P9U97T[#&:aTgilASokS@]/.4*qr+GYdaS*LRfdG>]hBc46]?&JbujS_(<u^_NYj0m/dtC7HA*$,6N90*D;V'V[L?<7dO<7fTuIi+<jrd"f!BAUsn7e[fJI_kG_eP>#+!8d6;AdI5pT^_u"&EGFVK5?O`D9%@=Ijt<E)9YIR]LZhu+&6<T6r,JB62\T71IUJ55d?]T2OUQ-m1Gf-%+>$&;b/O9a<M2fS=^RjEW>3u9Z,.8f_*$)'/(^NMb"(t(Y(Kk[[C\M`+#kaJj(qu_k@8mB%WbQ/(fo7i51$C_Ah[Up_4WCB`L%5c4`CsE</IlDH[T6im;*W%JnG0U@T=ua:=OJ3peoiuLU!(jNQC2Ym%@J.dVbqOKQC4m-KW3tTlRQ,8>L'1'N(dU0G9ihX5O/+B6a'C+-ja>Iubgh\TN?Y1^Ks6@Afi`@XmOQ*Ia/dUk7g'"4ABMfXdL\knr&0)1@OciMj7pa?acXJZf`5HU=R=gcpRtA%]h6XO_nU68nP[?o$l'!Uu&HX11omiA^6['V3-0md=9K5Lb*3WF[P`FXI3o.9cIPbm^NA"(H!rg'V83UG/BofKh\b=$/(:A`'4F\QPs#;23K)YsOWAiAKIVhf&"Q9!mQj>ca+.@H%&>e_8l:`p;8S+f1.-FGA9aOT\eom(o_X?8gW4_SMY!neg69)!#"di_O`4>O)N"pYs.kALGOrI/afO`afS++3A?D+sDXFJKu\i-V-7VYa*uZ-G'ja/e/8aFW,]$%dn'$]_/<m40J%!,o506o(#VJ&`iauP*_A,OF+up6RlDD*R:mXnaP"Bb@1a3?@FkBL:1n>QFLXNV.BgcqbeK&Rbk+j,9</tEr73J(6]<c*H)DfnI5*LLW:l*q@>.?$5E~>endstream
+endobj
+11 0 obj
+<<
+/Filter [ /ASCII85Decode /FlateDecode ] /Length 1460
+>>
+stream
+GatU2_/A!e&A@6Wk-W5_>h="de316+$S8N?[YQRsdaUfs9T]ZRg$sOicB+3*0+o/l_EhS^1AU(WHZ(6`)83?N?e,3a=7Ga,#2'ts"_<PU!`jfe\(0$P<Rs>/BaOOW3B^'.:$7W;>^8cQb_F$t)6E+F;AN'>kAtOTD:.`:P\:+$iA[uYSad7jN=uS@K>p\PR%3#;%B[Z"X=AnO$4Y-FCN=M\ci_FT&1ZuXV"MRqDgmJl1T^S+Rp$\0X+/PB=Mq:>)SlZT23\qEpBB2-1i35jast=?$:T_?0[p"TWr*[H:92-6S>lMUc/O3i"<h@B7%cI^@,6JGrnb([#R;82Yu(fpru<64Qn'[-@5[8h6-\jO!k#$rJD?kXf7C*"Ri.,MC)!UsN-,JWVQUWXmShc;:dM6(b+Pi(J?d$=otf4*577)OoC>5H#e;W8,P)oa\iBhc?66=EiJDO9WarcfUFng"?pR%h8I8Wi-+6>g@n!A;*:;Es^SCHl$Yq;p9,Fb%_Lc<e`'68F1/#sP2/,%-!Uup[F\uWe/bW-<>BhVUa]A4'kJMqj7V-f6R[nR?^nOY'd5C)*Oj,McEIU:F//a_Q@MnGUc.\T&K16K\1-W3+G/Yh=8%2'*!knlk+?$JrM3ajB_FcS5Sj]t"bS?C->0Pu)QUrP.//WlFACM^9cRI5NMHP>;&oQ2W"jEalD5?_)r7&S#k5%#]816uHSY+C%3u%7f^;#qdaNU3`TBPpIDD_7:Cp?V[BUcjN/n1-sOe=J74f(?62)(H(Q=>mqdq,(*7ra<f-mOUhG%^!6ntp%abbj([mdoftXEIi)qpn[gA*8_ErnTtuiXM3h<ihs-@`u<hF6%LXckU*\;b\\fb%boo_2PREX,PfFF"-o[]:K37%r`mikY"R.M*TWYDC2V:LP7K#^\4c[KL??<P<l#6kgM=3Ir9[BnVMn`q1qQJV$:MsOfd6;dQ&>lA+6Gnd?`U#(Co]D:&$1`70mS7i;p<o_Ss&9+J>ZI,1Pqm9tnI-D:5?/Wf3Yt$'Q\BXJ#(UPG-,=V=KRo1:7(lc-)Oj+GJB$7J>=iXI6Xf;*$Qu'(s/ikU:*-@*3a:o5U"Rq>H"2rV;cCOt-!%E=9>V*UacN=DVY/=WX,RM)a0oU_]cc4XJgb%nAIb/ZXGi^h"PAE0q2#73p:%T/12nA;_:`j)r[$S6eF=9G[;dC*G.B-^O'D?\WKLJuDGh+JH0l\in<gL8<b>Xqcb<'Qp_"dHKRQOG4WaH6c'C;8h%+MCI$.G$NeTZL`&Xj_pso+n&A/hb_lgOG/:\dJo"`m0]Vt/H2Q"%RK8>-TbX]H)5iHpV#u.$/9,$ndY+KlmNPOM;js_7X(LZb2?rY)s-DP`q<(M?VDQdh2W5tPP8nMEiaP'Rjl]bT-fH!KaU#BC7CtnY)jC#pq1Ck&2H)^AVtb5%$g17S>W^Rg6m+Wff*]>ks$K2e\@=E\+K~>endstream
+endobj
+12 0 obj
+<<
+/Filter [ /ASCII85Decode /FlateDecode ] /Length 1200
+>>
+stream
+GatU2bAQ>u']%q&mOi5>Wg7*ADKhLXdS3Q2Kf35be<Rs?,#sf3X2"*H.G;gNhuPsE@Fu89pY>A5F'@Uha%tA%I4FKJkFD*pb*qlq[\<8G5*n5.hW4:P`uR>0$;AHA<`"+sjp!@-dq2$DAY4.gj%^+nT=]Ts88m3%l.?>mlU\?mkCfBskUI(*Er+@"oPQ!kEi*L,.c!oO*.En']E$7l2Yr!I="8]q473><AQ4DT_X`_fL9W+#B!g(XJZWTF>NQ%??[-u%GJCa">hS*V]`54u^]:j67Y=]EWhJGfm70r](coVNGsbmtO7G+k77F)N:@*s7kkhXV=>\"F:B4BZ#jKI?er3<rY@H,TXSn$`n^M$F]*rSj:>j]Clq:lY"KVUp&_J];4/e,;k(@]sBLb;7$Oa"$`he<rgP;gU@`_@.8FNKc:TbMbZTUUWRB+#_Df_7I\C#?FcI(9'[n>O._a-kp-ks&Xgd,a'r+-=Ro.'uN[S4AJPRKnJTai&:;J=Q)a2$38;Fo`AqFXabp7Fh)<G>mW#\cOM*s<^GpACP\g/uu4?bGYap;.H\L'*b(5q50W[%AJ[`#.%Uo[k4G\NB:lX_]&]1r?d=\6u:[cOqRJ,cFXs:s.4JN'>-,'.$s-Yn_6scqZGM(^uA8fT.hFTeFOnVt1<VJc#_J@WN9[T@_cmfDFCtOil^C0::=NdRR+.:aiX5W-h5hA4ps+h*T<5!iR!qeI"CBrD7ce:kpSehu!O`*=o39Y!T`c)W]n<=F(;4rGMQSkllqK1St8bY$$KA:'u,+Lu=c<?t2m<e/f?Y+j66`FM`D57j=$iF?'jBTCh:l2F<H;bu)4l+`3*P1(0fK]@!o'6YmpRSe>+k:+@=!'jBAhY;YheAuo*lM@i)9HRHD[U4J8P*(2a&o"hek11lC[Rer'qpY>5j`p4'm?5el_:CTu`@O"0*:[*tF+E@Q;<$in3d*?+*6'HP(3g\5mE2/nTLd]jk)D_0<*)D@.'4/pIE*b!?DkfH_bR,k)(c:)3Mepk+IB5M:A9/rQ2ib5gTJS\>buElu_U/iK8TjdE6h6Qq>81./EDUMQC7hdkg_$DnC;cX/F!O&a^!MQc)`i45MI.W]WYI:r;AMXYC48M<c5sZO_ChlJJ,GlPS_4"Z?YA:7d>/bffa4^r5G&bIR.q].0P/IT:IcM<GCLrcXqV0,VCs[Nc2ZArn^d~>endstream
+endobj
+xref
+0 13
+0000000000 65535 f 
+0000000073 00000 n 
+0000000114 00000 n 
+0000000221 00000 n 
+0000000333 00000 n 
+0000000527 00000 n 
+0000000721 00000 n 
+0000000915 00000 n 
+0000000983 00000 n 
+0000001266 00000 n 
+0000001337 00000 n 
+0000002699 00000 n 
+0000004251 00000 n 
+trailer
+<<
+/ID 
+[<97c859a97ff504bbb736067c0d697b14><97c859a97ff504bbb736067c0d697b14>]
+% ReportLab generated PDF document -- digest (http://www.reportlab.com)
+
+/Info 8 0 R
+/Root 7 0 R
+/Size 13
+>>
+startxref
+5543
+%%EOF

package/package.json

@@ -0,0 +1,19 @@
+{
+  "name": "atris",
+  "version": "1.0.0",
+  "description": "Universal codebase instrumentation for AI agents",
+  "main": "bin/atris.js",
+  "bin": {
+    "atris": "./bin/atris.js"
+  },
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "keywords": ["ai", "agents", "codebase", "documentation", "automation"],
+  "author": "Keshav Rao (atrislabs)",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/atrislabs/atris.md.git"
+  }
+}