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 agents/willackerly/rebar/subagent-prompts-indexgit clone --depth 1 https://github.com/willackerly/rebarWhat 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 | $0.00000 | $0.00728 |
| Opus 5 | $0.00000 | $0.00364 |
| Sonnet 5 | $0.00000 | $0.00146 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
subagent-prompts-index 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 3d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Prompt Index
Catalog of available subagent templates. Each entry links to the full
template in subagent-prompts/.
Scaffolding
| Template | Description | LOE | Mode |
|---|---|---|---|
| _example-template | Annotated example — copy this to create new templates | — | — |
Reviews
| Template | Description | LOE | Mode |
|---|---|---|---|
| ux-review | Structured UX audit: accessibility, interaction, responsive, visual consistency, error states, interaction stability | High | single |
| security-surface-scan | Security audit: input validation, auth, crypto usage, data exposure, dependencies, red team mode | Max | single or fan-out |
| code-review | Multi-dimensional code review: correctness, performance, security, maintainability, style | High | single or fan-out |
| product-review | Product alignment: BDD coverage, persona fit, user flow completeness, scope assessment | High | single |
| red-team | Multi-persona adversarial review: 5 personas stress-test a component simultaneously | Max | single or fan-out |
Analysis
| Template | Description | LOE | Mode |
|---|---|---|---|
| contract-audit | Verify implementations conform to declared interfaces — methods, behavior, error contracts, test coverage | Max | single or fan-out |
| cleanroom-audit | Spec-vs-implementation audit with zero context — finds bugs the author missed (proven 4-bug ROI) | High | single |
| rebar-compliance-audit | Full REBAR compliance assessment (v3-aware) — structural, content accuracy, enforcement, session lifecycle | High | single or fan-out |
| doc-drift-detector | Compare doc claims against code reality — stale status, broken refs, contradictions, missing docs | Medium | single or fan-out |
| feature-inventory | Exhaustive behavioral inventory of a file/module — prerequisite before assigning worktree agents to large files | Medium | single |
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.
- 3d ago First seen · 56 lines · 0 tokens per session scan A 54aab26aebd1
subagent-prompts-index is an agent published in the GitHub repository willackerly/rebar (5 stars, last pushed 21d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 728 tokens. 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 2026-08-31.
Other agents, from other repositories
html_to_pdf_system_prompt
You are an "HTML slide export agent." Your job is not to design pages. Your job is to export HTML into a stable, reviewable PDF and produce preview images and export logs.
architect
Keep the solution inside a single Python module with one immutable data structure and one scoring function. Reject invalid numeric values before computing the score.
developer
Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.
headless-browser
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for web application navigation with headless browser.
observability
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an observability and monitoring stack (Grafana/Prometheus/Alertmanager/Splunk/Kibana-Elastic-Logstash-Fleet/Zabbix/Wazuh).
vpn-remote-access
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for remote-access infrastructure (OpenVPN/WireGuard/IPsec/SSL-VPN portals plus RDP/VNC/WinRM/SSH bastions/Apache Guacamole: key material, tunnel establishment, internal reachability).