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 3yesore/LetUenforskills --skill asa-evidence-grounding-auditorgit clone --depth 1 https://github.com/3yesore/LetUenforskillsWrote 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/3yesore/letuenforskills/asa-evidence-grounding-auditor)<a href="https://agentmods.dev/skills/3yesore/letuenforskills/asa-evidence-grounding-auditor"><img src="https://agentmods.dev/badge/skills/3yesore/letuenforskills/asa-evidence-grounding-auditor/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/3yesore/letuenforskills/asa-evidence-grounding-auditor"><img src="https://agentmods.dev/badge/skills/3yesore/letuenforskills/asa-evidence-grounding-auditor.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 | $0.00030 | $0.01208 |
| Opus 5.5 | $0.00012 | $0.00483 |
| Sonnet 5.5 | $0.00006 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
asa-evidence-grounding-auditor 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASA Evidence Grounding Auditor
Use this internal meta-skill when a model must decide whether a skill analysis is trustworthy enough to publish or reuse.
This skill fixes the failure mode where a fluent report hides unsupported claims, weak evidence, copied passages, overconfident inference, or unsafe anchors selected for reuse.
Inputs
- Deterministic inventory and source snapshot.
- Structure analysis and workflow analysis artifacts.
- Evidence objects attached to claims and workflow steps.
- Quality rule outputs when available.
Process
- List the major claims made by the analysis.
- Classify each claim as
explicit,structural,inferred,unsupported, orconflicting. - Check whether high-confidence claims have direct evidence.
- Check whether inferred claims are marked as inferred and use cautious confidence.
- Detect vague evidence, missing source paths, copied long passages, and quote overuse.
- Identify claims that sound plausible but only come from model reasoning.
- Convert reusable review findings into evidence, risk, confidence, and unsupported-claim anchors.
- Rate publishability as
publishable,needs_revision, orblocked. - Write concise remediation notes for every major or blocker issue.
Output Contract
Return evidence audit content suitable for review_report.json:
evidence_audit:
supported_claims: []
inferred_claims: []
unsupported_claims: []
missing_evidence: []
conflicts: []
publishable:
rationale:
anchors:
evidence_anchor:
- id:
claim_id:
evidence_kind: direct_quote | structural_inventory | workflow_order | resource_reference | test_output | model_inference
source_path:
quote:
supports:
limitations: []
reusable_as: quality_gate | citation_pattern | review_note | learning_note
confidence: high | medium | low | unknown
risk_anchor:
- id:
risk_type: over_inference | missing_evidence | copied_passage | runtime_claim | trigger_conflict | unsafe_reuse | stale_context
affected_claims: []
severity: high | medium | low
mitigation:
blocks_reuse: true | false
evidence: []
confidence_anchor:
- id:
target_id:
target_kind: claim | workflow_step | resource_role | reuse_asset | composition_candidate
confidence: high | medium | low | unknown
confidence_basis: direct | structural | inferred | conflicting | absent
downgrade_reason:
upgrade_requirements: []
evidence: []
unsupported_claim_anchor:
- id:
claim:
why_unsupported:
likely_source: model_reasoning | missing_source | ambiguous_text | contradicted_by_source | unknown
recommended_action: remove | rewrite_as_inference | add_evidence | block_publish
safe_reuse: true | false
evidence: []
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 · 142 lines · 30 tokens per session scan A fd0d30f5bbcf
asa-evidence-grounding-auditor is a skill published in the GitHub repository 3yesore/LetUenforskills (2 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 1,208 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 2026-08-31.
Other skills, from other repositories
impl-validator
Independently check whether an implementation matches its stated goal and return PASS/WARN/FAIL with actionable issues. Use for second-opinion validation of an implementation or generated output.
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
code-simplifier
Cleanup pass that edits the working tree — over a session's uncommitted changes, or a named path or whole codebase. Reads git diff (or the named target) and simplifies, consolidates, and aligns code with the existing codebase — modernize syntax, cut unnecessary complexity and slop, consolidate duplicated logic, catch…
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.