Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/hex/claude-council/deep-executionnpx skills add hex/claude-council --skill deep-executiongit clone --depth 1 https://github.com/hex/claude-councilWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hex/claude-council/deep-execution)<a href="https://agentmods.dev/skills/hex/claude-council/deep-execution"><img src="https://agentmods.dev/badge/skills/hex/claude-council/deep-execution.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00061 | $0.01196 |
| Opus 5 | $0.00030 | $0.00598 |
| Sonnet 5 | $0.00012 | $0.00239 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
deep-execution scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent-Enhanced Council Execution
Use parallel Claude subagents for deeper analysis. Each subagent queries its provider, evaluates response quality, can ask follow-up questions, and returns structured insights.
Step 1: Determine Provider Details
For each selected provider, gather:
- Provider name and script path:
${CLAUDE_PLUGIN_ROOT}/scripts/providers/{name}.sh - Model name: run
bash ${CLAUDE_PLUGIN_ROOT}/scripts/query-council.sh --list-availableor read the provider script defaults
Step 2: Spawn Provider Agents in Parallel
Launch ALL provider agents in a single message (multiple Agent tool calls) for parallel execution.
Use run_in_background: true and subagent_type: "general-purpose" for each.
Agent prompt template: See agent-prompt-template.md for the full template.
Read it and fill in {PROVIDER}, {SCRIPT_PATH}, and {QUESTION} for each agent.
CRITICAL: If a role was assigned to a provider (via --roles), build the
role-injected question with the same helper the standard flow uses — source
scripts/lib/prompts.sh and scripts/lib/roles.sh, then
build_prompt_with_role "<question>" "<role>" — and pass its output as the
agent's {QUESTION}. The role format itself is defined in
${CLAUDE_PLUGIN_ROOT}/prompts/role-injection.md.
CRITICAL: If file context was gathered (via --file or auto-context), include it in the question passed to each agent.
Step 3: Collect and Validate Results
As each background agent completes, you will be automatically notified. Wait for ALL agents to complete before proceeding to display.
If an agent fails or times out, note the failure and continue with available results.
Validate each agent's reply against the contract before using it. Write the
reply to a file first (its JSON may contain quotes, backticks, and $() that an
inline echo would let the shell mangle or execute), then feed it on stdin:
cat > /tmp/council-reply.json <<'COUNCIL_REPLY_EOF'
<paste the agent's raw JSON reply here, verbatim, unescaped>
COUNCIL_REPLY_EOF
bash ${CLAUDE_PLUGIN_ROOT}/scripts/validate-analysis.sh < /tmp/council-reply.json
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 139 lines · 61 tokens per session scan A d107dba72511
deep-execution is a skill published in the GitHub repository hex/claude-council (673 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,196 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
architect
System design, tradeoffs, and complex technical decisions.
scope-analyst
Catch ambiguities and hidden requirements before planning.
security-analyst
Threat-model and find vulnerabilities, with practical remediation.
code-reviewer
Find bugs, security holes, and maintainability issues in a diff or file.
plan-reviewer
Validate that a work plan is executable before work starts.
researcher
Research external libraries, APIs, and best practices, with evidence.