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 wefio/NodeMemoryGraph --skill verification-traceabilitygit clone --depth 1 https://github.com/wefio/NodeMemoryGraphWrote 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/wefio/nodememorygraph/verification-traceability)<a href="https://agentmods.dev/skills/wefio/nodememorygraph/verification-traceability"><img src="https://agentmods.dev/badge/skills/wefio/nodememorygraph/verification-traceability/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/wefio/nodememorygraph/verification-traceability"><img src="https://agentmods.dev/badge/skills/wefio/nodememorygraph/verification-traceability.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 | $0.00041 | $0.01596 |
| Opus 5.5 | $0.00016 | $0.00638 |
| Sonnet 5.5 | $0.00008 | $0.00319 |
| Haiku 4.5 | $0.00004 | $0.00160 |
Grade A, and why
verification-traceability 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 25d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification traceability
The rules — every assertion resolves to a check, no orphan checks, the coverage
table in the receipt, the frozen rule — are owned by
the requirements-traceability decision
and enforced by rtm:check. Do not restate them here.
This Skill covers only the judgement those cannot enforce: what to assert, and which kind of check supports it.
Author one assertion per claim
One assertion is one claim a reviewer can read plus the evidence that supports
it. Keep statement in the agent's words — it briefs the agent. Keep check
executable — it judges the agent.
assertions:
- id: daemon-does-not-depend-on-rcp
statement: NMG daemon and Core do not depend on or own the RCP
stage: unit
check: node-test:daemon-cli
kind: test
Place the assertion on the chain
A check proves one link, not the chain: requirement, acceptance, implementation,
unit, integration, E2E, deployment, observability, real-effect metric. Name the
stage the assertion actually verifies, and never let a unit test stand in for an
outcome. Evidence may be node-test:, eval:, metric:, review:, or
documented-only. When the last links are owned outside this repository, say so
and mark the assertion documented-only rather than borrowing someone else's
signal.
Scope the assertion to its evidence
A check is a sample, not coverage. State the context the evidence actually
covers — platform, entry points, inputs, version matrix — and do not let the
statement claim more. "The two bin entry points start on this platform" is
checkable; "the package works" is not, and belongs in documented-only.
Choose the cheapest kind that can actually fail
| Situation | kind |
Why |
|---|---|---|
| You can write the expected output | test |
most direct |
| A relation holds for all inputs | property |
examples are a sample; properties are not |
| The condition must hold while running | runtime-assertion |
design-by-contract; fails at the boundary, not only in a suite |
| No expected output exists | metamorphic |
assert a relation between runs instead of a value |
| The claim is about structure, not behaviour | coverage |
statement, branch, MC/DC |
| Pure logic where "for all inputs" matters | proof |
Dafny or LemmaScript |
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.
- 25d ago Changed · +3 lines e47f769a8c03
- 1mo ago Changed · +43 lines 82d20ac679a8
- 1mo ago First seen · 95 lines · 41 tokens per session scan A 92d11885bba6
verification-traceability is a skill published in the GitHub repository wefio/NodeMemoryGraph (0 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,596 once invoked, about $0.0002 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 2026-09-10.
Other skills, from other repositories
test-runner
For a code change, pick the right test tier by change surface, run apc test with baseline diff, and report only NEW reds vs baseline back to the task's acceptance criterion. Separates envblocked from SUT red so a broken machine never fails the code.
test-cases
Generate test cases from a Jira ticket's acceptance criteria. Produces e2e test scenarios (steps and expected results, no code) and a unit test checklist for developers. Test cases map back to requirements for traceability. Use when: "write test cases", "generate tests", "e2e tests for PROJ-789", "test cases for this…
test-strategy-document
Create a production-ready Testing Strategy and QA Execution Plan. Covers testing levels (unit, integration, E2E, performance), mocking boundaries, test environment matrix, code coverage thresholds, and automated CI pipeline runsheets. Use when establishing a QA framework for a new system or feature set.
source-command-swarm-testing
Migrated source command swarm-testing.
source-command-sparc-tester
Migrated source command sparc-tester.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.