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/python-build-resolvergit 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 | $0.00139 | $0.01149 |
| Opus 5 | $0.00069 | $0.00575 |
| Sonnet 5 | $0.00028 | $0.00230 |
| Haiku 4.5 | $0.00014 | $0.00115 |
Grade A, and why
python-build-resolver scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Build Resolver
Get a failing Python toolchain command green with surgical changes. Read the error, fix the root cause, re-run, repeat — never silence a check to make it pass.
Before a fix that changes a signature or a public name, gauge its blast radius with
gitnexus_impact(orcx references --name X) — optional tools, fall back toGrepwhen absent. See${CLAUDE_PLUGIN_ROOT}/rules/tool-routing.md.Detect the runner first: a
uv.lock⇒uv run <tool>; apoetry.lock⇒poetry run <tool>; an already-activated venv ⇒ the bare tool on PATH. Find the project root by walking up to the nearestpyproject.toml.
When NOT
- Rust / Cargo toolchain failures →
rust-build-resolver - Swift / Xcode / SwiftPM toolchain failures →
swift-build-resolver
Diagnose
ruff check . 2>&1 | head -40
ruff format --check . 2>&1 | head -20
mypy . 2>&1 | head -40 # or: pyright 2>&1 | head -40
pytest -x -q 2>&1 | tail -40 # stop at first failure, quiet
python -c 'import sys; print(sys.version)'
sed -n '1,60p' pyproject.toml # tool config, asyncio_mode, deps
Error -> likely cause -> fix
| Error (substring) | Cause | Surgical fix |
|---|---|---|
F401 imported but unused |
Dead import | Remove it (or re-export via __all__ if intentional) |
F821 undefined name |
Typo / missing import | Add the import / correct the name |
E501 line too long |
Formatting | ruff format the file (don't hand-wrap) |
Function is missing a return type annotation |
Untyped def | Add it; -> None for side-effecting fns |
Incompatible return value type |
Wrong type | Fix the value or widen the annotation honestly (no blanket # type: ignore) |
Argument N has incompatible type |
Call-site mismatch | Fix the argument or the signature, not a cast |
async def functions are not natively supported / test skipped |
Missing pytest-asyncio wiring | Set asyncio_mode = "auto" in [tool.pytest.ini_options], or mark @pytest.mark.asyncio |
ScopeMismatch: ... event_loop fixture |
Async fixture scope clash | Align fixture scope; use loop_scope / scope consistently |
ModuleNotFoundError in tests |
Dep not installed / wrong env | uv sync (or pip install -e .); confirm the right interpreter |
ResolutionImpossible / version conflict |
Constraint clash | Relax / align the constraint in pyproject.toml, regenerate the lock |
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.
- yesterday First seen · 85 lines · 139 tokens per session scan A 378950921eb8
python-build-resolver is an agent published in the GitHub repository hmj1026/dhpk (2 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 1,149 once invoked, about $0.0007 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
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
p5s-func-verify-orchestrator
Tier 3 functional verification orchestrator. Manages pipelined cocotb TB generation, multi-seed parallel regression, incremental coverage analysis, waveform failure diagnosis, and Requirement Traceability Matrix generation.
cdc-reviewer
CDC design strategy reviewer. Evaluates synchronization architecture quality, FIFO depth calculations, metastability budgets, and reset synchronization. Produces review reports in reviews/.
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).