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 skills/qwerfunch/cladding/oraclenpx skills add qwerfunch/cladding --skill oraclegit clone --depth 1 https://github.com/qwerfunch/claddingWhat 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 | $0.00082 | $0.01265 |
| Opus 5 | $0.00041 | $0.00633 |
| Sonnet 5 | $0.00016 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
oracle 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cladding oracle — impl-blind conformance authoring
A SPEC_CONFORMANCE oracle is a conformance test authored without seeing the implementation, so a passing oracle means "matches the spec," not "matches the code." The A/B that motivated this: a blind oracle caught bugs a code-peeking (sighted) oracle rubber-stamped (7/8 vs 4/8). cladding owns no LLM — the blinding is your discipline as the host; cladding produces the brief, records provenance, and the gate audits it.
Which ACs need an oracle? (the policy)
A project sets its requirement under spec.yaml::project:
oracle_policy: { always_ears: [unwanted], sample: 0.2 }(RECOMMENDED) — risk-weighted: author an oracle for every done AC whose EARS category is inalways_ears(default['unwanted']— error/edge handling), PLUS a deterministic ~samplefraction of the rest. v8 showed exhaustive per-AC oracles add ~0 quality at ~30% cost, so spot-check the bulk and concentrate verification where failures cluster.require_oracles: true— EXHAUSTIVE (every done AC). Highest assurance, highest cost.oracle_policytakes precedence when both are set.- Neither — no mandate (an authored oracle still runs + is recorded; a missing one is not forced).
Run clad oracle --required to print the worklist — exactly which done ACs the policy demands an oracle
for, which already have one, and why (always:<ears> / sample / exhaustive). Author oracles for the
← needs an impl-blind oracle rows only; do NOT author for ACs the policy did not select.
Protocol (three steps — do them in order)
-
Get the spec-only brief. Run
clad oracle <featureId> --ac <acId>. It prints the acceptance criterion- the module's declaration-only signatures — and NEVER an implementation body. This is the only thing the author may see.
-
Spawn a FRESH, blind sub-agent (the Task tool / a new sub-agent context) handed ONLY that brief. It MUST NOT read
src/or any implementation file. Instruct it to write a vitest conformance suite that asserts only what the criterion literally requires — when the spec is silent on an edge, a WEAKER assertion, not a stronger guess (an over-strict oracle falsely fails correct code). The sub-agent's identity must differ from whoever implemented the feature.
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 · 70 lines · 82 tokens per session scan A 11e111ac0a49
oracle is a skill published in the GitHub repository qwerfunch/cladding (14 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 1,265 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
map-plan
ARCHITECT phase - decompose complex tasks into atomic subtasks with research, spec, and branch-scoped plan artifacts under .map.
map-review
Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.
map-debug
Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents — including failing or flaky tests (pytest AssertionError), crashes and segmentation faults, memory-corruption or memory errors in native/C…
map-learn
Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.
map-efficient
State-machine MAP execution workflow for Codex. Use when implementing an approved MAP plan end to end, resuming from branch MAP taskplan or stepstate.json artifacts, or running non-trivial multi-subtask work. Use map-fast for tiny one-shot edits.
map-task
Execute a single subtask from an existing MAP plan via Actor and Monitor. Use when map-plan has decomposed work and you want fine-grained control over one subtask. Do NOT use without an existing plan; run map-plan first.