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 agentmods add skills/bankszach/document-systems/render-document-viewnpx skills add bankszach/document-systems --skill render-document-viewgit clone --depth 1 https://github.com/bankszach/document-systemsWhat 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 | $0.00062 | $0.00423 |
| Opus 5 | $0.00031 | $0.00211 |
| Sonnet 5 | $0.00012 | $0.00085 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
render-document-view 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 yesterday.
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.
What it actually says
Render Document View
Render a bounded projection of an existing Expression. Do not use a view as a replacement for its immutable semantic source.
Workflow
- Confirm that the input is an Expression envelope. If it is raw prose or
an unstructured need, use
compose-document-systemfirst. - Name the stakeholder and concern.
- Call
validate_document_expression. - Stop on integrity errors. For a consequential
HUMAN_ACTIONview, also stop when semantic assertions are absent or fail; warnings may remain visible in a draftHUMAN_REVIEWview. - Select one view:
HUMAN_REVIEW: full proposal with epistemic labels and limitations;HUMAN_ACTION: action-relevant authority, roles, states, transitions, requirements, gates, exceptions, and handoffs;MACHINE: canonical JSON projection for another deterministic consumer.
- Call
render_document_view. - Return the artifact separately from its manifest and validation receipt.
Boundaries
- Never add facts that are absent from the Expression.
- Never hide unresolved exceptions or missing evidence to improve appearance.
- Never label a rendered proposal operative, persistent, or accepted.
- Fail closed on
HUMAN_ACTIONwhen structural readiness is incomplete. - Keep element identifiers and source links stable across views.
- Return to the Expression when a view reveals a missing or conflicting element.
- Renderer-owned prose is limited to title, section labels, proposal banner, and limitation notice.
Output contract
Return the artifact, its content digest, source Expression identity, view manifest, validation receipt, included element IDs, and explicit omission reasons.
What ships with it
1 file 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.
- yesterday First seen · 45 lines · 62 tokens per session scan A 2baddd7feb7c
render-document-view is a skill published in the GitHub repository bankszach/document-systems (0 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 423 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 2026-08-31.
Other skills, from other repositories
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步(architecture-sync)。OpenCode / Claude / Codex / Cursor 通用。.
taiyi-diagram-c4
TaiyiForge 辅助 — 从代码反推 C4 架构文档(Observed/Inferred 分层 · Mermaid 真源)。OpenCode / Claude / Codex / Cursor 通用。.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.
steer
Project-profile recalibration. Audits session calibration drift, presents per-cluster evidence for a user verdict, writes the updated project-profile rule, and inscribes a settled-direction clause.