Borrowing it
Nothing to install: this file belongs to albertomarturelo/sii. 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/albertomarturelo/sii/main/.agents/skills/validate-context/SKILL.mdgit clone --depth 1 https://github.com/albertomarturelo/siiWrote 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/albertomarturelo/sii/validate-context)<a href="https://agentmods.dev/skills/albertomarturelo/sii/validate-context"><img src="https://agentmods.dev/badge/skills/albertomarturelo/sii/validate-context/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/albertomarturelo/sii/validate-context"><img src="https://agentmods.dev/badge/skills/albertomarturelo/sii/validate-context.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 | $0.00064 | $0.00558 |
| Opus 5.5 | $0.00026 | $0.00223 |
| Sonnet 5.5 | $0.00013 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
validate-context 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
Validate the CFD context in this project. Check, in order, and output a checklist with PASS / WARN / FAIL per item:
CLAUDE.mdsize: WARN if >150 lines, FAIL if >300.CLAUDE.mdcontent shape: should be mostly@references, not paragraphs of prose. FAIL if any section has >10 lines of inlined content where an@docs/...reference would do.docs/ROADMAP.mdfreshness: rungit log -1 --format=%ar -- docs/ROADMAP.md. WARN if it predates the last feature commit onmain— a shipped surface whose row was never ticked. (Do NOT checkdocs/CURRENT_STATUS.md: it is untracked since #79, so any git-based check reports it as infinitely stale.)- ADR index integrity: every file matching
docs/decisions/[0-9]*.mdmust be listed indocs/decisions/_index.md, and every row in_index.mdmust point to a file that exists. FAIL on mismatch. - ADR completeness: every ADR has Status, Context, Decision, Alternatives Considered, Consequences sections. FAIL on any ADR missing one.
- Convention coverage: spot-check 3 random source files. Do their
patterns match
docs/CONVENTIONS.md? If not, propose updates to CONVENTIONS.md (do not auto-apply). - Surface boundary (ADR-003): spot-check that
packages/cliandpackages/mcpimport only@albertomarturelo/sii-core's task layer (+ port interfaces), never a portal/dte/auth/storage facade directly. Flag any reach-past — it bypasses the throttling / audit / credential rails. - Language check: any
docs/**/*.mdfile written in a non-English language? WARN per file.
Output the checklist and propose concrete fixes for any failures. Do NOT auto-apply fixes — the user reviews first.
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 · 39 lines · 64 tokens per session scan A 9fc459435a26
validate-context is a skill published in the GitHub repository albertomarturelo/sii (16 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 558 once invoked, about $0.0003 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 2026-10-24.
Other skills, from other repositories
jira
Operate Jira Cloud via its REST v3 API — issues, projects, sprints, boards, comments, transitions, JQL search. Use when the user wants to triage, bulk-update, report on, or otherwise interact with Jira programmatically without the MCP server installed.
linear
Query and mutate Linear issues, projects, cycles, teams, workflow states, and comments via its GraphQL API. Use when the user wants to read or change Linear data programmatically — without the MCP server, and without hand-navigating the Linear UI.
{{BUCKET}}-management
Skill "{{BUCKET}}-management" from damusix/atomic-claude, covering purpose, doc shape and frontmatter contract.
find-contact
A contact and company lookup for amoCRM, a customer-management system. It searches existing records, checks for duplicates, and can create a new contact or company with notes and related activity.
unsorted-triage
A workflow for sorting new incoming requests in amoCRM, a customer-management system. It checks for duplicates, turns a request into a sales deal, records its context, and assigns a follow-up task.
complete-task
A workflow for completing or reassigning ELMA365 business-process tasks. ELMA365 is a business process management system in which tasks move a process from one step to the next.