Borrowing it
Nothing to install: this file belongs to infraspecdev/tesseract. 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/infraspecdev/tesseract/main/.claude/skills/updating-plugin-assets/SKILL.mdgit clone --depth 1 https://github.com/infraspecdev/tesseractWrote 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/infraspecdev/tesseract/updating-plugin-assets)<a href="https://agentmods.dev/skills/infraspecdev/tesseract/updating-plugin-assets"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/updating-plugin-assets/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/infraspecdev/tesseract/updating-plugin-assets"><img src="https://agentmods.dev/badge/skills/infraspecdev/tesseract/updating-plugin-assets.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 | $0.00054 | $0.01783 |
| Opus 5.5 | $0.00022 | $0.00713 |
| Sonnet 5.5 | $0.00011 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
updating-plugin-assets 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 2mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Updating plugin assets
Overview
Every plugin-asset change in tesseract/ must ship with an executable eval that exercises the new or changed behavior. In-conversation GREEN dispatches are necessary but not sufficient — they don't survive into the repo and can't regression-test future changes. This skill is the procedural companion to the Eval coverage — MANDATORY policy in CLAUDE.md.
Authoritative reference: shield/evals/README.md.
Related skills
REQUIRED SUB-SKILL when editing a SKILL.md: Use superpowers:writing-skills for skill-content quality (CSO, frontmatter, structure, pressure-test methodology). This skill and writing-skills are complementary, not alternatives — writing-skills covers how to write a good skill; this skill covers how to ship the change in this repo. Load both.
When to use
Trigger this skill whenever you are about to write or edit:
**/skills/**/SKILL.md**/agents/*.md**/commands/*.md**/.mcp.jsonor MCP server prompts under*/server/**/hooks/*and**/scripts/*that hooks invoke- Skill-orchestrator wiring (the prompts a skill uses to dispatch subagents)
- Anything under
shield/evals/(the eval system itself)
When NOT to use
- Pure doc edits (README typo, comment rewording, link fix)
- Renames with no behavior change
- Dependency bumps with no prompt/behavior change
For these, state "no eval-shaped surface" in the PR body and proceed.
Doc-authoring skills — writing-style contract
If the asset you are adding or editing is a doc-authoring skill (it writes a
doc to docs/shield/ — e.g. prd-docs, plan-docs, lld-docs, research, or
any future equivalent), it MUST include an explicit step that applies
shield:writing-style to its author-written prose before writing. Prose only —
never rendered/marker-wrapped sections or JSON sidecars. This is part of the
definition of done for such skills, alongside eval coverage.
Workflow
Before step 1: verify the asset actually exists at the path the user named and the section/symbol you intend to change is real. If the path or section name is wrong, surface the mismatch and ask — do not silently re-target. Following procedure on the wrong file is worse than not following procedure at all.
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.
- 2mo ago First seen · 131 lines · 54 tokens per session scan A d545c9b1a2de
updating-plugin-assets is a skill published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,783 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.