hail-hydra-cc 2.3.2 → 2.4.1

package/files/agents/hydra-analyst.md

@@ -4,7 +4,7 @@ description: >
   🔵 Hydra's analysis head — thorough code review, debugging, and analysis agent. Use
   PROACTIVELY whenever Claude needs to review code for quality, analyze a bug with error
   messages or stack traces, evaluate dependencies, assess test coverage, review pull request
-  changes, identify performance issues, or analyze technical debt. Runs on Sonnet 4.6 for strong
+  changes, identify performance issues, or analyze technical debt. Runs on Sonnet for strong
   reasoning at good speed.
   May run in parallel with other Hydra agents — produces self-contained, clearly structured
   output so the orchestrator can merge results from multiple simultaneous agents.

package/files/agents/hydra-coder.md

@@ -4,8 +4,8 @@ description: >
   🔵 Hydra's implementation head — capable code writing and engineering agent. Use PROACTIVELY
   whenever Claude needs to write new code, implement features, refactor existing code, create
   or modify tests, fix bugs with clear error messages, make API integrations, or perform any
-  code writing task that follows well-understood patterns. Runs on Sonnet 4.6 for a strong balance
-  of speed and capability. Use this for all standard implementation work — reserve Opus 4.6 only
+  code writing task that follows well-understood patterns. Runs on Sonnet for a strong balance
+  of speed and capability. Use this for all standard implementation work — reserve Opus only
   for novel architecture or extremely subtle debugging.
   May run in parallel with other Hydra agents — produces self-contained, clearly structured
   output so the orchestrator can merge results from multiple simultaneous agents.

package/files/agents/hydra-git.md

@@ -4,7 +4,7 @@ description: >
   🟢 Hydra's git operations specialist. Handles all version control tasks: staging,
   committing with well-crafted Conventional Commits messages, branching, merging,
   rebasing, stashing, cherry-picking, log inspection, diff analysis, and conflict
-  detection. Runs on Haiku 4.5 — git operations are mechanical and well-defined.
+  detection. Runs on Haiku — git operations are mechanical and well-defined.
   Use hydra-analyst for merge conflict RESOLUTION (requires code
   comprehension) but hydra-git for conflict DETECTION and all other git operations.
   May run in parallel with other Hydra agents — produces self-contained, clearly

package/files/agents/hydra-guard.md

@@ -2,11 +2,11 @@
 name: hydra-guard
 description: >
   🟢 Hydra's security and quality gate agent. Automatically invoked after hydra-coder
-  (Sonnet 4.6) produces code changes. Performs a fast scan for common security issues
+  (Sonnet) produces code changes. Performs a fast scan for common security issues
   (hardcoded secrets, SQL injection, XSS, unsafe deserialization, exposed API keys),
   code quality checks (unused imports, dead code, missing error handling on async
   operations), and leftover debug artifacts (console.log, TODO/FIXME/HACK comments).
-  Runs on Haiku 4.5 for speed — this is a fast gate, not a deep audit. For deep
+  Runs on Haiku for speed — this is a fast gate, not a deep audit. For deep
   security review, use hydra-analyst instead.
   May run in parallel with other Hydra agents — produces self-contained, clearly
   structured output so the orchestrator can merge results from multiple simultaneous agents.
@@ -91,7 +91,7 @@ areas of the codebase.
 - `src/api.py:88` — Unhandled promise rejection in `fetchUser()` — add try/catch
 - `src/utils.py:14` — TODO comment left in production path
 
-Note: Savings calculated against Opus 4.6 ($5/$25 per MTok). These are warnings only — code has been delivered above.
+Note: Savings calculated against Opus ($5/$25 per MTok). These are warnings only — code has been delivered above.
 ```
 
 ## Boundaries

package/files/agents/hydra-runner.md

@@ -4,7 +4,7 @@ description: >
   🟢 Hydra's execution head — fast test runner, build executor, and validation agent.
   Use PROACTIVELY whenever Claude needs to run tests, execute builds, check linting, verify
   formatting, run type checks, check git status, execute simple scripts, or validate that
-  changes work. Runs on Haiku 4.5 for speed — ideal for quick feedback loops during development.
+  changes work. Runs on Haiku for speed — ideal for quick feedback loops during development.
   May run in parallel with other Hydra agents — produces self-contained, clearly structured
   output so the orchestrator can merge results from multiple simultaneous agents.
 tools: Read, Bash, Glob, Grep

package/files/agents/hydra-scout.md

@@ -6,7 +6,7 @@ description: >
   files, read code, find patterns, grep for strings, list directories, understand project
   structure, answer "where is X?" questions, or build/update the codebase dependency map.
   This is the first head to reach for when gathering information before making changes.
-  Runs on Haiku 4.5 for near-instant responses.
+  Runs on Haiku for near-instant responses.
   May run in parallel with other Hydra agents — produces self-contained, clearly structured
   output so the orchestrator can merge results from multiple simultaneous agents.
 tools: Read, Grep, Glob, Bash, Write

package/files/agents/hydra-scribe.md

@@ -4,7 +4,7 @@ description: >
   🟢 Hydra's documentation head — fast technical writing agent. Use PROACTIVELY whenever
   Claude needs to write or update README files, add code comments or docstrings, create
   changelogs, write API documentation, update configuration docs, or produce any technical
-  writing that describes existing code. Runs on Haiku 4.5 for speed — documentation from
+  writing that describes existing code. Runs on Haiku for speed — documentation from
   existing code is largely descriptive and doesn't need heavy reasoning.
   May run in parallel with other Hydra agents — produces self-contained, clearly structured
   output so the orchestrator can merge results from multiple simultaneous agents.

package/files/agents/hydra-sentinel-scan.md

@@ -3,7 +3,7 @@ name: hydra-sentinel-scan
 description: >
   Fast integration sweep after code changes. Checks for broken imports,
   missing exports, changed function signatures, missing env vars, circular
-  dependencies, and changed API routes. Runs on Haiku 4.5 for speed.
+  dependencies, and changed API routes. Runs on Haiku for speed.
   If issues are found, the orchestrator escalates to hydra-sentinel for
   deep analysis. If clean — done, zero additional cost.
 model: haiku
@@ -206,6 +206,24 @@ Parallel-safe. Self-contained output. See SKILL.md collaboration rules.
 
 After scan completes, orchestrator handles sentinel-pending flag cleanup per SKILL.md sentinel protocol.
 
+### End-of-Scan Tracking Cleanup (REQUIRED)
+
+After producing your final report — clean OR issues_found OR error —
+ALWAYS clear the sentinel pending flag and write a scan marker so the
+statusline can show `✅ Sentinel clean` briefly:
+
+```bash
+SID="${CLAUDE_SESSION_ID:-unknown}"
+DIR="${TMPDIR:-/tmp}/hydra-sentinel"
+rm -f "${DIR}/${SID}-pending.json" 2>/dev/null
+mkdir -p "$DIR" 2>/dev/null
+date +%s > "${DIR}/${SID}-last-scan" 2>/dev/null
+```
+
+If `CLAUDE_SESSION_ID` is not set, clear the most recently modified
+`*-pending.json` in that directory and write the corresponding `-last-scan`
+marker. Failure here must not block your report — silently skip on error.
+
 ## Output Format — Compressed (MANDATORY)
 
 You report to the orchestrator (Opus), NOT to the user. Opus translates for the user. Output must be DENSE and STRUCTURED, not prose.

package/files/agents/hydra-sentinel.md

@@ -4,7 +4,7 @@ description: >
   Deep integration analysis triggered when sentinel-scan flags issues.
   Validates inter-component contracts, traces data flow across boundaries,
   confirms or dismisses findings from the fast scan, and provides specific
-  fix suggestions. Runs on Sonnet 4.6 for accuracy.
+  fix suggestions. Runs on Sonnet for accuracy.
 model: sonnet
 tools: Read, Grep, Glob, Write
 memory: project
@@ -208,3 +208,21 @@ Preambles, transitions, self-explanations, restatements, hedging, politeness.
 
 ### Role-specific
 Issue/fix pairs. Decision notes at confirm/dismiss only — one line each. Don't narrate the trace; show the conclusion.
+
+## End-of-Scan Tracking Cleanup (REQUIRED)
+
+After producing your final report — confirmed, dismissed, or mixed —
+ALWAYS clear the sentinel pending flag and write a scan marker so the
+statusline can show `✅ Sentinel clean` briefly:
+
+```bash
+SID="${CLAUDE_SESSION_ID:-unknown}"
+DIR="${TMPDIR:-/tmp}/hydra-sentinel"
+rm -f "${DIR}/${SID}-pending.json" 2>/dev/null
+mkdir -p "$DIR" 2>/dev/null
+date +%s > "${DIR}/${SID}-last-scan" 2>/dev/null
+```
+
+If `CLAUDE_SESSION_ID` is not set, clear the most recently modified
+`*-pending.json` in that directory and write the corresponding `-last-scan`
+marker. Failure here must not block your report — silently skip on error.

package/files/commands/hydra/config.md

@@ -1,37 +1,37 @@
----
-description: Show current Hydra configuration and how to customize it
-allowed-tools: Read, Bash
----
-
-# Hydra Config
-
-Show the current Hydra configuration:
-
-1. Check for project-level config first:
-```bash
-   cat .claude/skills/hydra/config/hydra.config.md 2>/dev/null
-```
-
-2. If not found, check global config:
-```bash
-   cat ~/.claude/skills/hydra/config/hydra.config.md 2>/dev/null
-```
-
-3. If neither found, show defaults:
-
-```
-🐉 Hydra Configuration (defaults — no config file found)
-─────────────────────────────
-Mode:          balanced
-Dispatch Log:  on
-Auto-Guard:    on
-Model Overrides: none
-─────────────────────────────
-To customize, create a config file:
-  Global:  ~/.claude/skills/hydra/config/hydra.config.md
-  Project: .claude/skills/hydra/config/hydra.config.md
-
-Run /hydra:status to see current agent assignments.
-```
-
-4. If a config file IS found, display its contents and note where it was loaded from.
+---
+description: Show current Hydra configuration and how to customize it
+allowed-tools: Read, Bash
+---
+
+# Hydra Config
+
+Show the current Hydra configuration:
+
+1. Check for project-level config first:
+```bash
+   cat .claude/skills/hydra/config/hydra.config.md 2>/dev/null
+```
+
+2. If not found, check global config:
+```bash
+   cat ~/.claude/skills/hydra/config/hydra.config.md 2>/dev/null
+```
+
+3. If neither found, show defaults:
+
+```
+🐉 Hydra Configuration (defaults — no config file found)
+─────────────────────────────
+Mode:          balanced
+Dispatch Log:  on
+Auto-Guard:    on
+Model Overrides: none
+─────────────────────────────
+To customize, create a config file:
+  Global:  ~/.claude/skills/hydra/config/hydra.config.md
+  Project: .claude/skills/hydra/config/hydra.config.md
+
+Run /hydra:status to see current agent assignments.
+```
+
+4. If a config file IS found, display its contents and note where it was loaded from.

package/files/commands/hydra/guard.md

@@ -1,71 +1,71 @@
----
-description: Manually run the Hydra security and quality scan on specified files or directories
-allowed-tools: Read, Grep, Glob, Bash
-model: haiku
----
-
-# Hydra Guard — Manual Security Scan
-
-Run a focused security and quality scan on the specified files.
-
-**Target**: $ARGUMENTS
-
-If no arguments provided, scan all files changed since the last commit:
-```bash
-git diff --name-only HEAD 2>/dev/null || echo "Not a git repository or no changes"
-```
-
-## Scan Checklist
-
-For each target file, check for:
-
-### CRITICAL (security)
-- Hardcoded secrets, API keys, tokens, passwords (patterns: `sk-`, `ghp_`, `AKIA`, `password =`, `secret =`, `token =`, `api_key =`)
-- SQL injection vulnerabilities (string concatenation in queries)
-- XSS vulnerabilities (unescaped user input in HTML output)
-- Unsafe deserialization (`eval()`, `pickle.loads()`, `unserialize()`)
-- Path traversal (`../` in file operations without validation)
-- Command injection (user input passed to shell commands)
-
-### WARNING (quality)
-- `console.log` / `print()` debug leftovers
-- TODO/FIXME/HACK comments
-- Unused imports (obvious cases only)
-- Missing error handling on async operations (no try/catch, no .catch())
-- Empty catch blocks
-- Hardcoded URLs or magic numbers without constants
-
-### INFO (style)
-- Functions longer than 100 lines
-- Deeply nested conditionals (3+ levels)
-- Inconsistent naming conventions within the same file
-
-## Output Format
-
-```
-🐉 Hydra Guard — Security & Quality Report
-═══════════════════════════════════════════
-Files scanned: 3
-
-🔴 CRITICAL (2 findings)
-  src/auth.py:45     Hardcoded API key: OPENAI_KEY = "sk-..."
-  src/db.py:78       SQL injection: f-string in query construction
-
-⚠️  WARNING (3 findings)
-  src/auth.py:12     console.log left in production code
-  src/utils.py:89    Empty catch block — errors silently swallowed
-  src/api.py:34      TODO: "fix this later" (line 34)
-
-ℹ️  INFO (1 finding)
-  src/handler.py:1   Function process_request is 142 lines long
-
-Summary: 2 critical · 3 warnings · 1 info
-```
-
-If no issues found:
-```
-🐉 Hydra Guard — All Clear ✅
-Files scanned: 3 | No issues found.
-```
-
-**Important**: This is a FAST scan, not a deep audit. For thorough security review, use hydra-analyst instead.
+---
+description: Manually run the Hydra security and quality scan on specified files or directories
+allowed-tools: Read, Grep, Glob, Bash
+model: haiku
+---
+
+# Hydra Guard — Manual Security Scan
+
+Run a focused security and quality scan on the specified files.
+
+**Target**: $ARGUMENTS
+
+If no arguments provided, scan all files changed since the last commit:
+```bash
+git diff --name-only HEAD 2>/dev/null || echo "Not a git repository or no changes"
+```
+
+## Scan Checklist
+
+For each target file, check for:
+
+### CRITICAL (security)
+- Hardcoded secrets, API keys, tokens, passwords (patterns: `sk-`, `ghp_`, `AKIA`, `password =`, `secret =`, `token =`, `api_key =`)
+- SQL injection vulnerabilities (string concatenation in queries)
+- XSS vulnerabilities (unescaped user input in HTML output)
+- Unsafe deserialization (`eval()`, `pickle.loads()`, `unserialize()`)
+- Path traversal (`../` in file operations without validation)
+- Command injection (user input passed to shell commands)
+
+### WARNING (quality)
+- `console.log` / `print()` debug leftovers
+- TODO/FIXME/HACK comments
+- Unused imports (obvious cases only)
+- Missing error handling on async operations (no try/catch, no .catch())
+- Empty catch blocks
+- Hardcoded URLs or magic numbers without constants
+
+### INFO (style)
+- Functions longer than 100 lines
+- Deeply nested conditionals (3+ levels)
+- Inconsistent naming conventions within the same file
+
+## Output Format
+
+```
+🐉 Hydra Guard — Security & Quality Report
+═══════════════════════════════════════════
+Files scanned: 3
+
+🔴 CRITICAL (2 findings)
+  src/auth.py:45     Hardcoded API key: OPENAI_KEY = "sk-..."
+  src/db.py:78       SQL injection: f-string in query construction
+
+⚠️  WARNING (3 findings)
+  src/auth.py:12     console.log left in production code
+  src/utils.py:89    Empty catch block — errors silently swallowed
+  src/api.py:34      TODO: "fix this later" (line 34)
+
+ℹ️  INFO (1 finding)
+  src/handler.py:1   Function process_request is 142 lines long
+
+Summary: 2 critical · 3 warnings · 1 info
+```
+
+If no issues found:
+```
+🐉 Hydra Guard — All Clear ✅
+Files scanned: 3 | No issues found.
+```
+
+**Important**: This is a FAST scan, not a deep audit. For thorough security review, use hydra-analyst instead.

package/files/commands/hydra/help.md

@@ -1,47 +1,47 @@
----
-description: Show all available Hydra commands, agents, and a quick reference guide
----
-
-# Hydra Help
-
-Display the following help reference directly — do NOT search files or run commands:
-
-```
-🐉 Hydra Framework — Quick Reference
-═══════════════════════════════════════
-COMMANDS
-  /hydra:help      Show this help screen
-  /hydra:status    Show installed agents, version, config
-  /hydra:update    Update Hydra to the latest version
-  /hydra:config    Show current configuration
-  /hydra:guard     Run security scan on files (usage: /hydra:guard src/auth.py)
-  /hydra:quiet     Suppress dispatch logs for this session
-  /hydra:map       View, rebuild, or query the codebase map
-  /hydra:verbose   Enable verbose dispatch logs with timing
-  /hydra:report    Report a bug, request a feature, or share feedback
-  /hydra:preflight Two-phase environment & compatibility check before new projects
-  /hydra:stats     Show real token usage and estimated savings (no AI estimation)
-  /hydra:stfu      Silence intermediate prose from every dispatched subagent
-
-AGENTS
-  🟢 hydra-scout    (Haiku 4.5)   — Explore codebase, find files, map structure
-  🟢 hydra-runner   (Haiku 4.5)   — Run tests, linters, build commands
-  🟢 hydra-scribe   (Haiku 4.5)   — Write docs, comments, READMEs
-  🟢 hydra-guard    (Haiku 4.5)   — Security scan, quality gate
-  🟢 hydra-git      (Haiku 4.5)   — Git operations, commits, branches
-  🟢 hydra-preflight (Haiku 4.5)  — Environment detection, version probing, dep inventory
-  🔵 hydra-coder    (Sonnet 4.6)  — Write and edit code
-  🔵 hydra-analyst  (Sonnet 4.6)  — Debug, diagnose, review
-
-HOW IT WORKS
-  The Opus 4.6 orchestrator automatically delegates tasks to cheaper,
-  faster agents (Haiku 4.5 and Sonnet 4.6) — saving ~50% on API costs
-  while maintaining Opus-level quality through verification.
-
-  You don't need to do anything. Just work normally.
-  Hydra operates invisibly unless you check the dispatch log.
-
-LINKS
-  GitHub:  https://github.com/AR6420/Hail_Hydra
-  npm:     https://www.npmjs.com/package/hail-hydra-cc
-```
+---
+description: Show all available Hydra commands, agents, and a quick reference guide
+---
+
+# Hydra Help
+
+Display the following help reference directly — do NOT search files or run commands:
+
+```
+🐉 Hydra Framework — Quick Reference
+═══════════════════════════════════════
+COMMANDS
+  /hydra:help      Show this help screen
+  /hydra:status    Show installed agents, version, config
+  /hydra:update    Update Hydra to the latest version
+  /hydra:config    Show current configuration
+  /hydra:guard     Run security scan on files (usage: /hydra:guard src/auth.py)
+  /hydra:quiet     Suppress dispatch logs for this session
+  /hydra:map       View, rebuild, or query the codebase map
+  /hydra:verbose   Enable verbose dispatch logs with timing
+  /hydra:report    Report a bug, request a feature, or share feedback
+  /hydra:preflight Two-phase environment & compatibility check before new projects
+  /hydra:stats     Show real token usage and estimated savings (no AI estimation)
+  /hydra:stfu      Silence intermediate prose from every dispatched subagent
+
+AGENTS
+  🟢 hydra-scout    (Haiku 4.5)   — Explore codebase, find files, map structure
+  🟢 hydra-runner   (Haiku 4.5)   — Run tests, linters, build commands
+  🟢 hydra-scribe   (Haiku 4.5)   — Write docs, comments, READMEs
+  🟢 hydra-guard    (Haiku 4.5)   — Security scan, quality gate
+  🟢 hydra-git      (Haiku 4.5)   — Git operations, commits, branches
+  🟢 hydra-preflight (Haiku 4.5)  — Environment detection, version probing, dep inventory
+  🔵 hydra-coder    (Sonnet 4.6)  — Write and edit code
+  🔵 hydra-analyst  (Sonnet 4.6)  — Debug, diagnose, review
+
+HOW IT WORKS
+  The Opus 4.6 orchestrator automatically delegates tasks to cheaper,
+  faster agents (Haiku 4.5 and Sonnet 4.6) — saving ~50% on API costs
+  while maintaining Opus-level quality through verification.
+
+  You don't need to do anything. Just work normally.
+  Hydra operates invisibly unless you check the dispatch log.
+
+LINKS
+  GitHub:  https://github.com/AR6420/Hail_Hydra
+  npm:     https://www.npmjs.com/package/hail-hydra-cc
+```

package/files/commands/hydra/quiet.md

@@ -1,16 +1,16 @@
----
-description: Suppress Hydra dispatch logs for the rest of this session
----
-
-# Hydra Quiet Mode
-
-Acknowledge this command and remember for the rest of this session:
-
-**Do NOT display the Hydra Dispatch Log footer after tasks.**
-
-Respond with:
-"🐉 Quiet mode enabled. Dispatch logs suppressed for this session. Use /hydra:verbose to re-enable."
-
-Continue operating Hydra normally (delegation, verification, auto-guard) — just don't show the dispatch log table.
-
-Also suppress the task completion notification sound for this session.
+---
+description: Suppress Hydra dispatch logs for the rest of this session
+---
+
+# Hydra Quiet Mode
+
+Acknowledge this command and remember for the rest of this session:
+
+**Do NOT display the Hydra Dispatch Log footer after tasks.**
+
+Respond with:
+"🐉 Quiet mode enabled. Dispatch logs suppressed for this session. Use /hydra:verbose to re-enable."
+
+Continue operating Hydra normally (delegation, verification, auto-guard) — just don't show the dispatch log table.
+
+Also suppress the task completion notification sound for this session.

package/files/commands/hydra/stats.md

@@ -80,6 +80,37 @@ const { stats, totalTurns, haikuCost, sonnetCost, opusCost,
         delegatedTurns, delegationRate, sessionFile, unknownModels } = summary;
 
 const bar = '━'.repeat(40);
+
+// No-delegation guidance branch — when no Hydra subagents dispatched OR savings below indicator threshold
+if (delegatedTurns === 0 || savedUSD < 0.01) {
+  console.log('');
+  console.log('🐉 Hydra Stats');
+  console.log(bar);
+  console.log('Session: ' + path.basename(sessionFile));
+  console.log('Turns:   ' + totalTurns);
+  console.log(bar);
+  console.log('');
+  console.log('🟣 Opus  (' + stats.opus.turns + ' turns):  ' + fmt(stats.opus.input + stats.opus.cache_create) + ' in / ' + fmt(stats.opus.output) + ' out  → \$' + opusCost.toFixed(3));
+  console.log(bar);
+  console.log('');
+  console.log('No Hydra subagent dispatches recorded in this session.');
+  console.log('');
+  console.log('Hydra works best when invoked explicitly. Try:');
+  console.log('  /hydra:scout       — codebase exploration on Haiku');
+  console.log('  /hydra:guard       — security scan on Haiku');
+  console.log('  /hydra:preflight   — environment validation');
+  console.log('  /hydra:map         — codebase dependency map');
+  console.log('');
+  console.log('Or include \"use hydra\" in prompts that involve multi-file');
+  console.log('exploration, codebase analysis, or routine verification.');
+  console.log(bar);
+  if (unknownModels && unknownModels.size > 0) {
+    console.log('');
+    console.log('⚠️  Unknown models (not counted): ' + Array.from(unknownModels).join(', '));
+  }
+  process.exit(0);
+}
+
 console.log('');
 console.log('🐉 Hydra Stats');
 console.log(bar);