vanara 0.2.0 → 0.3.0

package/catalog/agents/api-designer/AGENT.md

@@ -1,7 +1,7 @@
 ---
 name: api-designer
 description: Use when designing a new HTTP/GraphQL API or changing an existing one — modeling resources, defining endpoint contracts, choosing status codes, pagination, filtering, error envelopes, versioning, and idempotency. Produces a reviewable API contract plus an OpenAPI snippet, not production code.
-tools: Read, Grep, Glob
+tools: Read, Grep, Glob, Write
 model: claude-sonnet-4-6
 type: agent
 version: 2.0.0
@@ -138,3 +138,19 @@ this agent critiques a draft contract.
 Pairs with the [`rest-api-design`](../../skills/rest-api-design/SKILL.md) skill (the deep reference for
 the conventions applied here), the `api-documenter` agent (turns this contract into published docs), and
 the `security-auditor` agent (for the authz/threat review this agent deliberately leaves out).
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/api-designer.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/api-designer.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/code-reviewer/AGENT.md

@@ -166,3 +166,19 @@ These are the ways reviews go wrong. Actively guard against each:
 **Pairs with** the `security-auditor` agent for deep security
 audits, the `owasp-top10` skill for the vulnerability catalogue, and the `error-handling-patterns`
 skill for correct error propagation.
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/code-reviewer.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/code-reviewer.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/debugger/AGENT.md

@@ -110,3 +110,19 @@ Report in this structure:
 
 Pairs with the `code-reviewer` agent (review the fix before merge), the `tdd-guide` agent (turn the repro
 into a failing test first), and the `error-handling-patterns` skill (so the cause can't silently recur).
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/debugger.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/debugger.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/pr-summarizer/AGENT.md

@@ -154,3 +154,19 @@ migration. The PR is described as "add export auth," but it also changes the def
 **Pairs with** the `code-reviewer` agent (hand off for severity-ranked findings), the
 `security-auditor` agent (deep security review of flagged surface), and the `conventional-commits`
 skill (for authoring the PR title/body once the summary is written).
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/pr-summarizer.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/pr-summarizer.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/refactoring-specialist/AGENT.md

@@ -183,3 +183,19 @@ Do not use this agent when:
 - `scripts/detect-smells.mjs` — runnable Node check that flags long functions and deep nesting (`--selftest`)
 
 Pairs with the `refactoring-patterns` skill, the `code-reviewer` agent, and the `test-author` agent.
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/refactoring-specialist.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/refactoring-specialist.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/security-auditor/AGENT.md

@@ -166,3 +166,19 @@ The finding and remediation:
 **Pairs with** the [`threat-modeler`](../threat-modeler/AGENT.md) agent for design-time trust-boundary
 analysis, the [`vuln-scanner`](../vuln-scanner/AGENT.md) agent for automated SAST/dependency coverage, and
 the `owasp-top10` skill for the full vulnerability catalogue.
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/security-auditor.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/security-auditor.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/technical-writer/AGENT.md

@@ -161,3 +161,19 @@ Deliver the finished document with:
 
 Pairs with the `readme-writing` and `documentation-structure` skills for assembling docs into a coherent
 documentation set, and with `update-docs` for keeping generated docs in sync with their source.
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/technical-writer.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/technical-writer.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/test-author/AGENT.md

@@ -175,3 +175,19 @@ Pairs with the **e2e-playwright** skill (full browser journeys) and the **code-r
 agent (quality and security pass after tests are green). See
 [references/test-types-and-pyramid.md](references/test-types-and-pyramid.md) for where each
 layer belongs.
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/test-author.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/test-author.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/threat-modeler/AGENT.md

@@ -1,7 +1,7 @@
 ---
 name: threat-modeler
 description: Use when designing a new system or feature, or assessing the attack surface of an existing one. Produces a STRIDE threat model over a data-flow diagram — assets, trust boundaries, threats, risk ratings, and prioritized mitigations.
-tools: Read, Grep, Glob
+tools: Read, Grep, Glob, Write
 model: claude-opus-4-8
 type: agent
 version: 2.0.0
@@ -161,3 +161,19 @@ TRUST BOUNDARY: Internet  ││  Private network
 Pairs with the `security-auditor` agent (for code-level vulnerability findings), the `architect` agent
 (for the system design the model is built on), and the [`owasp-top10`](../../skills/owasp-top10/) skill
 (for mapping threats to the most common web weakness classes).
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/threat-modeler.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/threat-modeler.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/catalog/agents/vuln-scanner/AGENT.md

@@ -144,3 +144,19 @@ Security scanning fails in predictable ways. Guard against each:
 
 Pairs with the `security-auditor` agent, the `threat-modeler` agent, the `secrets-management` skill, and
 the `owasp-top10` skill.
+
+
+## Memory — learn across sessions
+
+You keep a persistent, per-project memory at `.claude/memory/vuln-scanner.md`. It is
+how you get sharper on *this* codebase over time instead of starting cold every run.
+
+- **Before you start:** read `.claude/memory/vuln-scanner.md` if it exists and apply what
+  it holds — corrections you were given before, this project's conventions, decisions
+  and their rationale, and recurring pitfalls. If it is missing, continue without it.
+- **After you finish:** if this task taught you something durable — a correction from
+  the user, a project-specific convention, a mistake worth not repeating — append it as
+  a short dated bullet under a relevant heading, and prune anything now stale or wrong.
+  Keep entries terse and general.
+- **Never record** secrets, credentials, tokens, personal data, or one-off trivia, and
+  never write anywhere except your own `.claude/memory/` file.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vanara",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "description": "Vanara — deploy packs of skilled AI agents. Install agents, skills, and packs into any project from the Vanara catalog.",
   "type": "module",
   "bin": {