Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sparq-org/sparqnpx agentmods add skills/sparq-org/sparq/access-controlWrote 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/sparq-org/sparq/access-control)<a href="https://agentmods.dev/skills/sparq-org/sparq/access-control"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/access-control.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Tool Misuse · line 214 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Agent Snooping · line 802 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 859 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00174 | $0.24456 |
| Opus 5 | $0.00087 | $0.12228 |
| Sonnet 5 | $0.00035 | $0.04891 |
| Haiku 4.5 | $0.00017 | $0.02446 |
Grade A, and why
access-control 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 4d 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 — 1,153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sparq-solid — graph-level WAC/ACP access control
sparq-solid is an opt-in crate that enforces Solid-style access control over a
sparq RDF dataset at the named-graph granularity. A pod is stored as
one named graph per document; the WAC (.acl) and ACP (.acr) access-control
documents stay as plain queryable triples; their semantics are encoded as N3 rules
(run by sparq-reason) that materialize a queryable authorization view in the
reserved <urn:sparq:auth> graph. Every query/update is then filtered per
(WebID, client, issuer) session to the named graphs that session may access —
fail-closed, with zero Solid-specific code in the engine itself (the crate is a
dependency of nothing in the workspace).
What this is — and is NOT (read first)
This is an architecture / research-track layer, not a deployable Solid server.
- It is the authorization half only. It answers "may this
(WebID, client, issuer)session read/append/write named graph G?" by materializing WAC/ACP into a queryable view and filtering the dataset. It does NOT authenticate: aSession.agentis a caller-asserted WebID string — there is no WebID-OIDC / DPoP / token verification. The relying application is responsible for authenticating the WebID before it hands one toquery_as. Treat aSessionas a trusted claim, not a verified one. - The
Session.issuerfield (ACPacp:issuer) does NOT add WebID-OIDC authentication. It is one more caller-asserted matcher dimension: the caller states which OIDC issuer it claims vouched for the WebID, and an ACPacp:issuermatcher decides whether that asserted issuer is acceptable. sparq-solid never contacts an IdP, validates an ID token, or verifies the issuer binding — it only string-matches the asserted issuer against the grant. As withagent, the relying application must verify the issuer↔WebID binding before asserting it. WAC has no issuer notion, so a WAC pod ignores the field entirely. - It is NOT a Solid Pod HTTP server. There is no HTTP resource protocol, no LDP
container CRUD, no
Link rel=acldiscovery over the wire, no Solid notifications. The document→named-graph naming is a storage convention (design §2.2), not an HTTP server. - The honest support matrix, threat model, security boundaries, and measured baseline
live in the design record
(
research/solid-access-control-design.md); the README's support matrix andcargo doc -p sparq-solidare the user docs. Do not present this crate as a production Solid implementation.
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.
- 4d ago Changed · +20 lines cea800054143
- 7d ago First seen · 1,133 lines · 174 tokens per session scan A 9d39e781693e
access-control is a skill published in the GitHub repository sparq-org/sparq (10 stars, last pushed 2d ago), licensed MIT. It adds 174 tokens to every session and 24,456 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.