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 CodeInfinity1/Stram --skill screenshot-ocr-reviewgit clone --depth 1 https://github.com/CodeInfinity1/StramWrote 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/codeinfinity1/stram/screenshot-ocr-review)<a href="https://agentmods.dev/skills/codeinfinity1/stram/screenshot-ocr-review"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/screenshot-ocr-review/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/codeinfinity1/stram/screenshot-ocr-review"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/screenshot-ocr-review.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 | $0.00036 | $0.00473 |
| Opus 5.5 | $0.00014 | $0.00189 |
| Sonnet 5.5 | $0.00007 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
screenshot-ocr-review 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot OCR Review
Purpose
Use screen captures as visual evidence for UI review, troubleshooting, and accessibility. This skill is careful about privacy and does not claim OCR unless a native OCR/tool path actually runs.
When To Use
Use when the user asks what is on screen, needs visual UI evidence, wants screenshot review, or asks to diagnose a visible app state.
Inputs And Evidence
- Active window or screen target.
- Screenshot filename, metadata, and sensitivity.
- User-requested review focus: layout, errors, text, controls, or visual state.
Tool Map
screenshot_capturescreen_capturesscreen_capture_deleteocr_provider_statusos_windowsos_observe_uibrowser_live_screenshottool_search
Workflow
- Prefer UIA/browser observations when text structure is available.
- Capture a screenshot only when visual evidence is needed and approved.
- Review visible state and note uncertainty.
- Use
ocr_provider_statusbefore OCR claims; run OCR only when a native extraction adapter is actually available. - Delete sensitive captures when they are no longer needed.
- Connect visual findings to the task outcome.
Native Implementation Boundaries
- Use Stram screen and browser screenshot tools.
- Do not import external reference OCR, computer-use, or screenshot scripts as implementation.
- Do not claim OCR/text extraction if only visual observation was performed.
Safety And Approval
- Screens can show private data; screenshot capture and deletion follow approval policy.
- Do not include secrets from screenshots in responses.
- Avoid broad screen capture in shared or sensitive contexts.
Verification
- Screenshot paths and metadata prove capture.
- Deletion tool result proves cleanup.
- UI text claims should come from UIA/browser observations or native OCR where available.
Failure Modes
- Keeping sensitive screenshots.
- Reading text inaccurately from visuals.
- Treating a screenshot as current after the UI changes.
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.
- 1mo ago First seen · 70 lines · 36 tokens per session scan A 436635e409c2
screenshot-ocr-review is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 473 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
omh-live-incident-response
This is an OMH live-incident-response workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
debugging
Use this skill when something is broken and the cause is unknown — a failing test, a crash, an error message, wrong output, a regression, a hang, or behaviour that differs between environments — and it has to be found and fixed at the root. Also use it to build the failing proof for a suspected defect before fixing…
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
postmortem
Deliver a structured post-mortem after incidents, mistakes, or stuck sessions. Use when the user requests a structured post-mortem after incidents, mistakes, or stuck sessions.