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 terrene-foundation/kailash-coc-claude-py --skill conformance-walkgit clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-pyWrote 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/terrene-foundation/kailash-coc-claude-py/conformance-walk)<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/conformance-walk"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/conformance-walk/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/terrene-foundation/kailash-coc-claude-py/conformance-walk"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/conformance-walk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 75 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 82 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00052 | $0.03287 |
| Opus 5 | $0.00026 | $0.01643 |
| Sonnet 5 | $0.00010 | $0.00657 |
| Haiku 4.5 | $0.00005 | $0.00329 |
Grade A, and why
conformance-walk 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 9d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conformance Walk (CW)
One-liner. ONE surface-agnostic core (cw_core) + a registry of per-surface adapters grouped into THREE oracle families on ONE delivery axis — source → shipped artifact → live behavior: SOURCE (SCM = Source Conformance Matrix — symbol holds its contract in source, judged without running), DELIVERED (DCM/FCM — the capability is reachable + non-stub in the SHIPPED artifact: wheel × binding × resolved feature set), LIVE (API / CLI / MCP / FE — a real invocation matches the frozen post-state). ONE discipline across all three: enumerate every actionable unit → attach a FROZEN expectation → judge observed state with a DETERMINISTIC oracle → report coverage HONESTLY (separate from pass-rate, machine-derived denominator) → RATCHET so a new unit without an expectation fails → TIER severity by surface-role. cw_core is built once; each surface supplies a small adapter. Users never choose "which family" — the matching adapter activates by the surface touched.
The delivery gap is the thesis. The dominant real-world failure is not "source lacks the feature" and not "the running service misbehaves" — it is source HAS the feature, tests PASS against source, yet the published artifact the user installs does NOT contain it (a capability gated off the default cargo feature set compiles out of the wheel; a binding wrapper is never generated). DELIVERED is the middle node nobody instruments. cw_core's record schema IS the interop boundary that lets a non-core-importing adapter conform (§6), and one capability record spans symbol (SCM) → delivered-node (DCM) → endpoint/tool/route (LIVE): a red delivered-node lights the WHOLE capability.
The four always-on MUST clauses are in rules/conformance-walk.md. This skill is the HOW: the methodology, cw_core + its JSON-schema interop boundary, the normative adapter-registry interface, the per-consumer adapter obligation, the three-family adapter table, the phase-action triggers, and the CW-vs-/redteam role split. Depth beyond the 80% here lives in three sub-files (loaded on demand): adapter-registry-interface.md, coverage-honesty-contract.md, reference-adapters.md.
What ships with it
4 files 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.
- 9d ago First seen · 108 lines · 52 tokens per session scan A e91aeeeaa39d
conformance-walk is a skill published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 24d ago), licensed Apache-2.0. It adds 52 tokens to every session and 3,287 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.