Borrowing it
Nothing to install: this file belongs to pvliesdonk/scholar-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pvliesdonk/scholar-mcp/main/.agents/skills/writing-model-facing-text/SKILL.mdgit clone --depth 1 https://github.com/pvliesdonk/scholar-mcpWrote 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/pvliesdonk/scholar-mcp/writing-model-facing-text)<a href="https://agentmods.dev/skills/pvliesdonk/scholar-mcp/writing-model-facing-text"><img src="https://agentmods.dev/badge/skills/pvliesdonk/scholar-mcp/writing-model-facing-text/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/pvliesdonk/scholar-mcp/writing-model-facing-text"><img src="https://agentmods.dev/badge/skills/pvliesdonk/scholar-mcp/writing-model-facing-text.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 | $0.00056 | $0.03138 |
| Opus 5.5 | $0.00022 | $0.01255 |
| Sonnet 5.5 | $0.00011 | $0.00628 |
| Haiku 4.5 | $0.00006 | $0.00314 |
Grade A, and why
writing-model-facing-text 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 23d 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.
This is a copy
91% identical to writing-model-facing-text — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing model-facing text
Every docstring and description= a FastMCP server registers is sent to
the client on the wire, and most of it reaches the model as a hint at one
moment: when it chooses a tool and fills in the arguments. Text the model
cannot act on at that moment is not harmless. It costs context on every
turn, Claude Code cuts each tool description and each server's
instructions at 2,048 characters and keeps the start, and a model told
about an operator command or a resource it cannot fetch acts on it anyway.
The evidence for every rule here is in
docs/design/reference/mcp-model-facing-text.md; read it before arguing
with a rule.
Who reads each surface
| Surface | Reader | Read when | What clients do with it |
|---|---|---|---|
| Tool description | the model | choosing a tool, filling arguments | put in the system prompt; Claude Code truncates at 2,048; tool search indexes it |
| Parameter description | the model | filling that one argument | property in the JSON schema; tool search indexes it |
Tool title, annotations |
the client | rendering a label, deciding whether to confirm | hints only; spec says clients must treat them as untrusted |
| Server instructions | the model | session start | system prompt; the one text Claude Code loads before any tool under tool search; truncated at 2,048; spec: should not duplicate tool descriptions |
| Resource description | a human in a picker, sometimes the model | browsing or attaching context | application-driven: the model may never see the list and often cannot fetch it |
| Prompt and prompt-argument descriptions | a human in a slash-command picker | picking a prompt | user-controlled |
| Tool result and error text | the model | after the call | the only surface that can say what to do next given the state |
| Skill served over MCP (SEP-2640) | the model, after the host lists its name and description and the model asks to load it | on demand, only on a host that implements the extension | skill:// resources; other clients see plain resources; hosts treat the body as untrusted data the user may refuse to load |
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.
- 23d ago First seen · 252 lines · 56 tokens per session scan A a93119c97e0e
writing-model-facing-text is a skill published in the GitHub repository pvliesdonk/scholar-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 3,138 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to writing-model-facing-text, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
servicenow-cmdb
Auditing the CMDB as a data model: CI class hierarchy, raw relationships, CMDB health scorecards, data quality (duplicates, orphans, staleness, missing fields) and CSDM 5 conformance. Use when the user mentions CMDB health, CMDB audit, data quality, duplicates, orphaned or stale CIs, CI classes, relationships in…
exploring-tables
Exploring any ServiceNow table: schema, field types, sample records, relationships, data patterns, a record's history (work notes, comments, field changes), and what touches a table or field (business rules, client scripts, UI policies, ACLs, script includes). Use when the user mentions tables, schemas, fields, data…
triaging-incidents
Creating, triaging, updating, and analyzing ServiceNow incidents, including trend reports. Assess severity, check affected CIs, find related incidents, and recommend assignments. Use when the user mentions incidents, INC numbers, outages, service disruptions, ticket creation, triage, priority, severity, ITSM…
analyzing-access
Reviewing who holds which ServiceNow roles and explaining access denials. Lists admin and securityadmin holders, roles granted directly instead of through groups, roles left on inactive or long-absent users, and diagnoses 401/403 errors, empty results and missing fields. Joins users, groups and roles through…
reviewing-update-sets
Reviewing, analyzing, and comparing ServiceNow update sets before promotion, singly or in batches. Shows changes, risks, dependencies, and conflicts. Use when the user mentions update sets, customizations, promotion, code review, change tracking, pre-deployment review, sysupdatexml, customer updates, 'what changed in…
assessing-change-impact
Assessing what a ServiceNow change request touched and what followed it: affected CIs, other changes on the same CIs in an overlapping window, and incidents on those CIs after the change, without trusting hidden incident-to-change links. Use this skill whenever the user asks whether a change (a CHG number) caused or…