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/hmj1026/dhpk/indexgit clone --depth 1 https://github.com/hmj1026/dhpkWhat 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 | $0.00018 | $0.05025 |
| Opus 5 | $0.00009 | $0.02513 |
| Sonnet 5 | $0.00004 | $0.01005 |
| Haiku 4.5 | $0.00002 | $0.00502 |
Grade A, and why
dhpk-agents-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 2d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Index (dhpk plugin)
36 agents shipped by the dhpk plugin (35 root-level +
polyfill-reviewerundermodules/library-author/agents/). Discovered asdhpk:<name>after install. The full list also appears in.claude-plugin/plugin.json.
Agent contract
Each role states its scope, entitlements, completion evidence, and next-role
handoff in its own file. This index owns roster and trigger navigation; the
frontmatter and rules/execution-policy.md remain the SSOT for registration,
precedence, and dispatch behavior.
Sentinel-driven reviewer dispatch (7-slot default, v0.10.0+)
Triggered reviewers — database-reviewer / security-reviewer / frontend-reviewer / code-reviewer / doc-reviewer / polyfill-reviewer / migration-reviewer — dispatch as one consolidated parallel batch per implementation wave (one message, multiple Agent calls); only triggered items run, and code/doc are not mutually exclusive. Findings are deduplicated into one fix batch; a known-finding re-review is confirm-only rather than another broad review. tdd-guide and e2e-runner are implementation specialists, not part of the unconditional post-edit batch. Triggered reviewers are armed automatically by post-edit-dispatch → post-edit-remind and reminded at Stop by stop-review-reminder.
| Agent | Model | When it fires |
|---|---|---|
| tdd-guide | sonnet | Test-first unit/integration work (AI-judgment, pre-edit): owns RED and scoped runs; implements GREEN only for a ≤2-production-file footprint, otherwise returns a fast-worker-ready fix-spec and later accepts with the scoped command |
| database-reviewer | sonnet | SQL / schema / migration / Repository edits |
| security-reviewer | sonnet | Auth / authz / crypto / file-upload edits |
| frontend-reviewer | sonnet | JS/TS edits when the js module is active; template-embedded <script> blocks (AI-judgment backfill) |
| code-reviewer | sonnet | Mandatory after any source-code Edit/Write |
| doc-reviewer | haiku | Edits under .claude/{agents,rules,commands,skills,manifests}/, docs/, openspec/, or top-level CLAUDE.md / AGENTS.md / README*.md — covers both frontmatter schema (name/model/tools) for .md DSL artifacts AND cross-file SSOT / link-validity checks |
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.
- 2d ago First seen · 156 lines · 18 tokens per session scan A f70c11061de6
dhpk-agents-index is an agent published in the GitHub repository hmj1026/dhpk (2 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 5,025 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
trellis-research
Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
p2-arch-orchestrator
Phase 2 architecture pipeline orchestrator. Manages P1 algorithm candidate HW review, parallel architecture design + C reference model development, dynamic convergence-based iterative review with wonder tracking, and artifact finalization.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).