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 dibun75/visor --skill visor-contextgit clone --depth 1 https://github.com/dibun75/visorWrote 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/dibun75/visor/visor-context)<a href="https://agentmods.dev/skills/dibun75/visor/visor-context"><img src="https://agentmods.dev/badge/skills/dibun75/visor/visor-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/dibun75/visor/visor-context"><img src="https://agentmods.dev/badge/skills/dibun75/visor/visor-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 | $0.00039 | $0.00357 |
| Opus 5.5 | $0.00016 | $0.00143 |
| Sonnet 5.5 | $0.00008 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
visor-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 5d 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.
What it actually says
V.I.S.O.R. Context
Use this skill when the task depends on locating relevant symbols or files in a repository and V.I.S.O.R. is available locally or through MCP.
First establish index health. In a terminal, run visor doctor and, if needed,
visor index. Do not install dependencies, change the retrieval mode, or write
IDE configuration unless the user explicitly asks. Lexical retrieval is the
safe default for offline and headless work.
For focused discovery, use visor context "<task or question>" --json or the
MCP build_context tool. Treat the returned snippets, line ranges, graph paths,
and retrieval reasoning as leads to verify against the working tree before
editing. Prefer visor trace for file-level dependency paths and V.I.S.O.R.'s
drift reporting when previously loaded context may be stale.
Keep the agent's context compact:
- Request context for the concrete task, not a broad repository summary.
- Read returned source files or symbols before relying on a result.
- Use native search and inspection if V.I.S.O.R. is unavailable, unindexed, or does not return a useful result.
- Do not claim token savings, correctness, or benchmark improvements from a single V.I.S.O.R. response.
After a change, use the repository's normal tests and review the diff. Reindex when source changes make the current index stale; do not assume a watcher is running in a terminal or CI environment.
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.
- 5d ago First seen · 34 lines · 39 tokens per session scan A d0e293acf5c7
visor-context is a skill published in the GitHub repository dibun75/visor (3 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 357 once invoked, about $0.0002 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 2026-11-01.
visor-context compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| visor-contextdibun75/visor | Skill | 3 | 3d ago | MIT | A | 39 | Claude Code, Codex |
| roamCranot/roam-code | Skill | 515 | 7d ago | Apache-2.0 | A | 86 | Claude Code |
| memorix-troubleshootingAVIDS2/memorix | Skill | 906 | yesterday | Apache-2.0 | A | 36 | Claude Code |
| enolaenola-labs/enola | Skill | 288 | yesterday | Apache-2.0 | A | 34 | Claude Code |
| narsilpostrv/narsil-mcp | Skill | 187 | 1mo ago | Apache-2.0 | A | 42 | Claude Code |
| trace-mcpnikolai-vysotskyi/trace-mcp | Skill | 202 | yesterday | MIT | A | 22 | Claude Code |
| m1nd-firstmaxkle1nz/m1nd | Skill | 24 | 14d ago | MIT | A | 78 | Claude Code |