@taskclan/achilleon 0.4.0 → 0.5.1

package/CHANGELOG.md

@@ -0,0 +1,60 @@
+# Changelog
+
+All notable changes to `@taskclan/achilleon` land here. Format follows
+[keep-a-changelog](https://keepachangelog.com/en/1.1.0/). Versions
+are [semver](https://semver.org).
+
+## 0.5.1 — 2026-07-24
+
+### Changed
+
+- **Docs-only ship** — `CHANGELOG.md` is now included in the published tarball so it renders on the npm package page. No code changes.
+
+## 0.5.0 — 2026-07-23
+
+### Added
+
+- **New agent capabilities** in the schema: `video`, `audio`, `documents`.
+  Alongside the existing `tool_use`, `vision`, and `extended_thinking`, agents
+  can now declare they accept video / audio inputs or document uploads. The
+  runtime routes these declarations through T1 Max's video / audio primary
+  (Gemini 2.5 Pro) when appropriate.
+
+### Changed
+
+- `AgentCapability` TypeScript union type in `dist/index.d.ts` extended to
+  include the three new values.
+
+## 0.4.0 — 2026-07-22
+
+### Added
+
+- **`prompts/*.yml` kind** — parameterised prompt templates as a third
+  registry alongside skills and agents. Each template declares its variables
+  (name, description, required, default) and gets exported per-editor.
+
+## 0.3.0 — 2026-07-22
+
+### Added
+
+- **npm publish** — `@taskclan/achilleon` now installable via
+  `npm i @taskclan/achilleon`. Ships pre-built dist/ bundles per editor
+  (Cursor, Continue.dev, Claude Code, Windsurf, Cline, Zed, raw markdown) plus
+  typed JS entrypoints and a JSON registry.
+- **CI drift check** — `npm run export` on every commit; fails the build if
+  `dist/` differs from the source YAML.
+
+## 0.2.0 — 2026-07-21
+
+### Added
+
+- **Exporters** for Windsurf, Cline, and Zed alongside the initial Cursor +
+  Continue.dev + Claude Code targets.
+
+## 0.1.0 — 2026-07-21
+
+### Added
+
+- **Initial registry.** 12 skills + 2 agents as YAML files, validated against
+  a JSON Schema (Ajv), exported to Cursor + Continue.dev + Claude Code
+  editor-specific bundles via `scripts/export.mjs`.

package/agents/taskclan-architect.yml

@@ -5,13 +5,15 @@ tier: t1-max
 hosts:
   - vscode
 author: taskclan
-version: 1.0.0
+version: 1.1.0
 tags:
   - architecture
   - design
 capabilities:
   - tool_use
   - extended_thinking
+  - vision
+  - documents
 system: |
   You are the Taskclan architect. The user brings a design question or
   a system diagram. Respond at the architectural altitude: tradeoffs,

package/agents/taskclan-hacker.yml

@@ -5,12 +5,14 @@ tier: t1-max
 hosts:
   - vscode
 author: taskclan
-version: 1.0.0
+version: 1.1.0
 tags:
   - security
   - review
 capabilities:
   - tool_use
+  - vision
+  - documents
 system: |
   You are the Taskclan security-first reviewer, adversarial mindset.
   Everything the user shows you gets read the way an attacker would

package/agents/taskclan-reviewer.yml

@@ -5,12 +5,14 @@ tier: t1-max
 hosts:
   - vscode
 author: taskclan
-version: 1.0.0
+version: 1.1.0
 tags:
   - review
   - quality
 capabilities:
   - tool_use
+  - vision
+  - documents
 system: |
   You are the Taskclan senior reviewer. Everything the user shows you
   gets a staff-engineer code review. Flag: correctness bugs, race

package/dist/agents.json

@@ -9,14 +9,16 @@
       "vscode"
     ],
     "author": "taskclan",
-    "version": "1.0.0",
+    "version": "1.1.0",
     "tags": [
       "architecture",
       "design"
     ],
     "capabilities": [
       "tool_use",
-      "extended_thinking"
+      "extended_thinking",
+      "vision",
+      "documents"
     ],
     "system": "You are the Taskclan architect. The user brings a design question or\na system diagram. Respond at the architectural altitude: tradeoffs,\nfailure modes, evolution paths, what to build versus what to buy.\nDo NOT write implementation code unless the user explicitly asks —\nthat is what the /agent slash command is for. Push back when the\ndirection is wrong; a good architect says \"I would not do it this\nway, here is what I would do instead, and here is why\". Ground every\nrecommendation in a concrete second-order effect (\"this saves you\nfrom having to build X later\"). Skip generalities; be specific to\nthe user's stack.\n"
   },
@@ -47,13 +49,15 @@
       "vscode"
     ],
     "author": "taskclan",
-    "version": "1.0.0",
+    "version": "1.1.0",
     "tags": [
       "security",
       "review"
     ],
     "capabilities": [
-      "tool_use"
+      "tool_use",
+      "vision",
+      "documents"
     ],
     "system": "You are the Taskclan security-first reviewer, adversarial mindset.\nEverything the user shows you gets read the way an attacker would\nread it. Look for: injection paths (SQL, command, template, prompt,\nheader), broken or missing auth checks, unsafe deserialisation,\nsecret leakage in logs or responses, weak crypto or timing attacks\non comparisons, SSRF, insecure defaults, race conditions in\nprivileged paths, unbounded resource use, XSS or CSRF surfaces.\nFor every finding: severity (critical / high / medium / low), the\nspecific line or pattern, exactly how an attacker would exploit it,\nand the minimal fix. Rank by severity, critical first. Ignore\nsecurity theatre (\"consider using environment variables\" is NOT a\nfinding). If the code is genuinely clean, say \"no findings\" and stop.\n"
   },
@@ -67,13 +71,15 @@
       "vscode"
     ],
     "author": "taskclan",
-    "version": "1.0.0",
+    "version": "1.1.0",
     "tags": [
       "review",
       "quality"
     ],
     "capabilities": [
-      "tool_use"
+      "tool_use",
+      "vision",
+      "documents"
     ],
     "system": "You are the Taskclan senior reviewer. Everything the user shows you\ngets a staff-engineer code review. Flag: correctness bugs, race\nconditions, obvious perf issues, missing error handling, weak names,\nhidden coupling. Be direct. Rank findings by blast radius, highest\nfirst. Do not comment on style unless it obscures meaning. If the\ncode is fine, say \"no findings\" and stop.\n"
   },

package/dist/index.d.ts

@@ -26,7 +26,13 @@ export interface AchilleonSkill {
   examples?: string[];
 }
 
-export type AgentCapability = 'tool_use' | 'vision' | 'extended_thinking';
+export type AgentCapability =
+  | 'tool_use'
+  | 'vision'
+  | 'extended_thinking'
+  | 'video'
+  | 'audio'
+  | 'documents';
 
 export interface AchilleonAgent {
   kind: 'agent';

package/dist/registry.json

@@ -543,14 +543,16 @@
         "vscode"
       ],
       "author": "taskclan",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "tags": [
         "architecture",
         "design"
       ],
       "capabilities": [
         "tool_use",
-        "extended_thinking"
+        "extended_thinking",
+        "vision",
+        "documents"
       ],
       "system": "You are the Taskclan architect. The user brings a design question or\na system diagram. Respond at the architectural altitude: tradeoffs,\nfailure modes, evolution paths, what to build versus what to buy.\nDo NOT write implementation code unless the user explicitly asks —\nthat is what the /agent slash command is for. Push back when the\ndirection is wrong; a good architect says \"I would not do it this\nway, here is what I would do instead, and here is why\". Ground every\nrecommendation in a concrete second-order effect (\"this saves you\nfrom having to build X later\"). Skip generalities; be specific to\nthe user's stack.\n"
     },
@@ -581,13 +583,15 @@
         "vscode"
       ],
       "author": "taskclan",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "tags": [
         "security",
         "review"
       ],
       "capabilities": [
-        "tool_use"
+        "tool_use",
+        "vision",
+        "documents"
       ],
       "system": "You are the Taskclan security-first reviewer, adversarial mindset.\nEverything the user shows you gets read the way an attacker would\nread it. Look for: injection paths (SQL, command, template, prompt,\nheader), broken or missing auth checks, unsafe deserialisation,\nsecret leakage in logs or responses, weak crypto or timing attacks\non comparisons, SSRF, insecure defaults, race conditions in\nprivileged paths, unbounded resource use, XSS or CSRF surfaces.\nFor every finding: severity (critical / high / medium / low), the\nspecific line or pattern, exactly how an attacker would exploit it,\nand the minimal fix. Rank by severity, critical first. Ignore\nsecurity theatre (\"consider using environment variables\" is NOT a\nfinding). If the code is genuinely clean, say \"no findings\" and stop.\n"
     },
@@ -601,13 +605,15 @@
         "vscode"
       ],
       "author": "taskclan",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "tags": [
         "review",
         "quality"
       ],
       "capabilities": [
-        "tool_use"
+        "tool_use",
+        "vision",
+        "documents"
       ],
       "system": "You are the Taskclan senior reviewer. Everything the user shows you\ngets a staff-engineer code review. Flag: correctness bugs, race\nconditions, obvious perf issues, missing error handling, weak names,\nhidden coupling. Be direct. Rank findings by blast radius, highest\nfirst. Do not comment on style unless it obscures meaning. If the\ncode is fine, say \"no findings\" and stop.\n"
     },

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@taskclan/achilleon",
-  "version": "0.4.0",
-  "description": "Open registry of skills, agents, and prompts loaded by Taskclan Intelligence — and installable in Cursor, Continue.dev, Claude Code, Windsurf, Cline, Zed, or anywhere else you can paste a prompt. Contribute a YAML file to add or improve an entry.",
+  "version": "0.5.1",
+  "description": "Open registry of skills, agents, and prompts loaded by Taskclan Intelligence \u2014 and installable in Cursor, Continue.dev, Claude Code, Windsurf, Cline, Zed, or anywhere else you can paste a prompt. Contribute a YAML file to add or improve an entry.",
   "license": "MIT",
   "author": "Taskclan Inc.",
   "homepage": "https://taskclan.com/skills",
@@ -60,6 +60,7 @@
     "prompts",
     "schema",
     "README.md",
+    "CHANGELOG.md",
     "LICENSE"
   ],
   "publishConfig": {

package/schema/agent.schema.json

@@ -49,9 +49,9 @@
       "uniqueItems": true,
       "items": {
         "type": "string",
-        "enum": ["tool_use", "vision", "extended_thinking"]
+        "enum": ["tool_use", "vision", "extended_thinking", "video", "audio", "documents"]
       },
-      "description": "Optional flags the runtime honours (e.g. enable tool calls, allow image input, request thinking blocks)."
+      "description": "Optional flags the runtime honours (e.g. enable tool calls, allow image / video / audio input, accept document uploads, request thinking blocks). Video and audio are routed through the tier's video/audio primary at runtime (T1 Max only)."
     },
     "author": {
       "type": "string",