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/codex-deep-reasonergit clone --depth 1 https://github.com/hmj1026/dhpkWrote 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/agents/hmj1026/dhpk/codex-deep-reasoner)<a href="https://agentmods.dev/agents/hmj1026/dhpk/codex-deep-reasoner"><img src="https://agentmods.dev/badge/agents/hmj1026/dhpk/codex-deep-reasoner.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 | $0.00021 | $0.00885 |
| Opus 5 | $0.00010 | $0.00443 |
| Sonnet 5 | $0.00004 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
codex-deep-reasoner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Deep Reasoner Compatibility Forwarder
This one-release compatibility entry point resolves to codex-reasoner in
read-only mode. New dispatches use the canonical role; legacy callers retain
requested_role=codex-deep-reasoner and effective_role=codex-reasoner
through the immutable role contract.
Follow agents/codex-reasoner.md for prompt composition, evidence, timeout,
read-only discipline, and reporting. Preserve its host-executable tools and
replace its direct adapter invocation with the canonical launcher below.
Forward through the canonical launcher
Invoke only the repository-owned launcher; it resolves the alias before starting the provider adapter:
node "${CLAUDE_PLUGIN_ROOT}/skills/dhpk-cli-dispatch-context/scripts/launch-cli-dispatch.js" \
--dispatching-agent "<dispatcher-role>" \
--execution-provider codex \
--requested-role codex-deep-reasoner \
--mode read-only \
--task-id "<task-id>" \
--attempt-id "<attempt-id>" \
--workdir "<absolute-workdir>" \
--prompt "<absolute-prompt-file>" \
--scope "<absolute-scope-json>" \
--config-layer "<absolute-config-json>"
The resulting context must retain requested_role=codex-deep-reasoner, resolve
effective_role=codex-reasoner, bind provider codex, and bind authority
read-only. The launcher exports DHPK_CLI_TRANSPORT_CONTEXT and starts the
selected adapter only after context construction returns READY. A missing or
contradictory role, mode, provider, authority, path, scope, transport, or receipt
is BLOCKED; never fabricate the context, widen authority, or call the adapter
directly.
The backend report is not reasoning evidence. Independently verify every cited
file:line against the working tree and confirm the run produced no working-tree
writes. Only a configured deterministic missing-executable fallback may change
backend; authentication, authorization, model, task, receipt, and evidence
failures remain BLOCKED.
Contained timeout result
For runner exit 124, accept timeout evidence only from a contained
dhpk.cli.receipt.v1 with terminal TIMEOUT; the receipt is never DONE or
success evidence. TIMEOUT_SALVAGED requires an independently verified before/after diff
and explicit reconciliation. A missing, invalid, or uncontained
receipt is BLOCKED. There is no automatic retry and no backend fallback.
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 · 87 lines · 21 tokens per session scan A ecdee81ec752
codex-deep-reasoner is an agent published in the GitHub repository hmj1026/dhpk (2 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 885 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
adversarial-reviewer
Plays "what could go wrong" against a Wave's diff. Surfaces race conditions, edge cases, silent failures, and operability gaps that other reviewers miss. Triggered LAST in the review pipeline (after spec-compliance and security have completed) so it can avoid duplicating their findings.
requirements-reviewer
Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…
security-reviewer
Reviews a Wave's diff for OWASP Top 10 vulnerabilities introduced in this change. Triggered automatically by /mumei:compose after a Wave is implemented. Demands HIGH confidence for non-critical findings — false positives erode trust. Does NOT cover code quality, spec, or correctness.
spec-compliance-reviewer
Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…
design-reviewer
Reviews a draft design.md against the approved requirements.md. Detects coverage gaps (ACs without a corresponding design element), missing architectural artifacts (no diagram, no Components, no Trade-offs), and Wave Plan defects (granularity unfit for tasks decomposition). Triggered automatically by /mumei:compose…
issue-validator
Re-validates a single finding produced by another reviewer with fresh context. Returns valid / invalid / unsure. Triggered by /mumei:compose after the 3 reviewers complete (spec-compliance / security / adversarial) — invoked once per finding in parallel for severity=HIGH/CRITICAL findings. Filters false positives…