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 uqeu/estelle-cli --skill evidence-traceability-auditgit clone --depth 1 https://github.com/uqeu/estelle-cliWrote 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/uqeu/estelle-cli/evidence-traceability-audit)<a href="https://agentmods.dev/skills/uqeu/estelle-cli/evidence-traceability-audit"><img src="https://agentmods.dev/badge/skills/uqeu/estelle-cli/evidence-traceability-audit/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/uqeu/estelle-cli/evidence-traceability-audit"><img src="https://agentmods.dev/badge/skills/uqeu/estelle-cli/evidence-traceability-audit.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 | $0.00000 | $0.01603 |
| Opus 5.5 | $0.00000 | $0.00641 |
| Sonnet 5.5 | $0.00000 | $0.00321 |
| Haiku 4.5 | $0.00000 | $0.00160 |
Grade A, and why
evidence-traceability-audit 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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
evidence-traceability-audit
Estelle's evidence-traceability skill, from Google Cloud AI Research's ScientistOne (arXiv:2605.26340,
project page scientist-one.github.io) and its Chain-of-Evidence design axiom "every
claim traceable to evidence." The mechanism inverts that axiom into an adversarial check: for every claim AND
every citation an answer already carries, RE-RESOLVE it against live recall — a [source] header that points at
nothing is a FABRICATED CITATION, and a number no cited source or green run reproduces is an UNREPRODUCIBLE
NUMBER. Any claim that can't be traced back fails the deterministic merge gate. It runs on the real primitives:
retrieve_cited (serve/memory_pipeline.py) returns (text, source_file) pairs; cite_block heads each with
its [source]; hybrid RRF (rrf_fuse / fuse_ranked_texts, serve/hybrid.py) does the recall; code_search
(serve/memory_facade.py) re-resolves a citation to an exact file:line with no embedding; GroundingReport.is_grounded
(agent/grounding.py) checks uncited claims against the real symbol graph; run_and_repair_suite /
parse_suite_output (agent/verify_suite.py) reproduce a claimed number from the repo's own suite; and
_gate_verdict (serve/api.py, POST /gate) returns merge: false. Distinct from atomic-fact-audit, which
LABELS each claim Supported/Unsupported/Contradicted and returns a FActScore precision number, and from
provenance-trail, which ATTACHES a receipts chain to an answer it already trusts: this skill is the trace-back
that HUNTS fabricated citations and unreproducible numbers and HARD-FAILS the gate on any untraceable claim.
When to run
Before shipping any answer, report, or PR description that CITES sources or quotes numbers — a benchmark result,
a "per orders.py …" attribution, a metric in a design note. It earns its keep exactly when the draft was written
with confident-looking citations, because a made-up [source] reads identically to a real one until you try to
resolve it. Run it on load-bearing, contestable output; skip it on trivia.
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.
- 1mo ago First seen · 73 lines · 0 tokens per session scan A a670d711e442
evidence-traceability-audit is a skill published in the GitHub repository uqeu/estelle-cli (0 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,603 tokens. 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 2026-09-12.
Other skills, from other repositories
cocosearch-review-pr
Use when reviewing a GitHub PR or GitLab MR by URL. Fetches diff and metadata via API, then uses CocoSearch for blast radius analysis, dependency impact, pattern consistency, and test coverage assessment. Read-only by default; optionally pushes findings back as inline PR/MR comments after your confirmation.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
code-review
You are a senior code reviewer. You receive diffs via stdin.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
review
Adversarial fresh-context review and risk check of an increment before it ships; every finding cites path:line and is re-verified. Use for "review", "qa", "quality check", "critique this".