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 skills add jstoup111/ai-conductor --skill build-review-implementation-qualitygit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/build-review-implementation-quality)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/build-review-implementation-quality"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/build-review-implementation-quality/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/build-review-implementation-quality"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/build-review-implementation-quality.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00025 | $0.00687 |
| Opus 5.5 | $0.00010 | $0.00275 |
| Sonnet 5.5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
build-review-implementation-quality 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Judge one engine-managed build_review implementation-quality rubric branch. This is a
judgement-only contract: the engine owns scope, input assembly, validation, identity, and verdict.
Input projection (v3)
Use only the supplied v3 projection. It identifies the frozen feature diff by reference. Read a
referenced file or git diff <mergeBase>..HEAD -- <path> when needed; do not use plan, story,
ADR, transcript, or prior-review content.
Judge only the reviewScope delta hunks. Treat changedFiles as context only. If that review
identifies a finding outside the delta, set causeHunk to the delta hunk that causes it.
Judgement
Report one finding per independent concrete defect. Anchor it to the changed hunk that introduces
the defect; name related unchanged code only in evidenceLocations.
A duplication or excess-complexity finding must be complete, because its repair consolidates in
one pass. Its summary names every repeated behavior or tangled flow the delta introduces for that
defect, and evidenceLocations lists every site that shares it. Do not report the most visible
instance and leave the remainder for a later lap.
duplication— newly repeated behavior creates divergent maintenance paths. Non-finding: a declared exact pattern replication or incidental short syntax repetition.excess-complexity— a changed control/data flow is unnecessarily difficult to follow, including four or more levels of nesting that can be flattened without changing correctness. Non-finding: ordinary conditional logic with clear bounded cases.obscured-intent— changed structure hides the domain operation it performs. Non-finding: a local implementation detail with an unambiguous name and boundary.primitive-obsession— changed primitive values encode a domain concept that needs invariants. Non-finding: a primitive whose valid range and meaning are already locally enforced.representable-invalid-state— changed state shape permits an invalid domain combination. Non-finding: states constrained at construction so invalid combinations cannot arise.non-exhaustive-domain-match— a changed domain branch silently drops a meaningful case. Non-finding: an explicit exhaustive default that preserves all remaining cases.non-semantic-name— a changed public or domain name obscures its semantic role. Non-finding: a short conventional iterator or a private implementation-local temporary.
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.
- yesterday Changed · +3 lines acba086eeaeb
- 2d ago Changed · +3 lines 2b318c2d5bc7
- 6d ago Changed · +3 lines ff96af87c322
- 17d ago First seen · 49 lines · 25 tokens per session scan A 7a1c2eef59e6
build-review-implementation-quality is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 687 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
sync-bridge
Reviews and guides Chromium Sync Model API (DataTypeSyncBridge) implementations, including DataTypeStore persistence and forwards/backwards compatibility for sync specifics. Use when implementing or reviewing a DataTypeSyncBridge subclass, DataTypeStore usage, sync metadata persistence, conflict resolution, or…
sync-model-processor
Reviews changes to Chromium Sync model internals in components/sync/model/, including ClientTagBasedDataTypeProcessor, ClientTagBasedRemoteUpdateHandler, ProcessorEntity, ProcessorEntityMetadata, and ProcessorEntityTracker. Use when modifying or reviewing processor state transitions, entity metadata tracking, conflict…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
gsd-ns-review
Invoke this Pi skill with /skill:gsd-ns-review.
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…