# Send Sightglass to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "sightglass", "name": "Sightglass", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/davidgeorgehope/sightglass", "canonicalUrl": "https://clawhub.ai/davidgeorgehope/sightglass", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/sightglass", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=sightglass", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "analyze.sh", "hooks/post-session.sh", "hooks/pre-spawn.sh", "setup.sh", "skill.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "sightglass", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-03T16:39:11.876Z", "expiresAt": "2026-05-10T16:39:11.876Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=sightglass", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=sightglass", "contentDisposition": "attachment; filename=\"sightglass-0.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "sightglass" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/sightglass" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/sightglass", "downloadUrl": "https://openagent3.xyz/downloads/sightglass", "agentUrl": "https://openagent3.xyz/skills/sightglass/agent", "manifestUrl": "https://openagent3.xyz/skills/sightglass/agent.json", "briefUrl": "https://openagent3.xyz/skills/sightglass/agent.md" } } ``` ## Documentation ### 🔍 Sightglass — Agent Supply Chain Intelligence Your AI coding agent just added 47 dependencies to your project. Do you know why it picked any of them? Sightglass instruments AI coding agents to capture every tool selection, dependency install, and architectural choice — then surfaces risks, biases, and better alternatives you never saw. ### Why This Matters When a human developer picks a dependency, there's a reasoning trail: blog posts read, alternatives compared, team discussions had. When an AI agent picks one, that trail is invisible. The agent "just knows" packages from training data — which means it's biased toward: Whatever was popular when training data was cut off Packages with the most Stack Overflow mentions (not the best packages) Dependencies it's seen in similar projects (not necessarily right for yours) Sightglass makes this invisible decision-making visible. ### Discovery Classification Sightglass classifies how your agent found each dependency: ClassificationWhat It MeansRisk LevelTRAINING_RECALLAgent just "knew" it from training data — no search performed🟡 MediumCONTEXT_INHERITANCEFound in existing project files (package.json, imports, etc.)🟢 LowREACTIVE_SEARCHAgent hit a problem and searched for a solution🟡 MediumPROACTIVE_SEARCHAgent actively compared alternatives before choosing🟢 LowUSER_DIRECTEDHuman explicitly told the agent what to use⚪ None High TRAINING_RECALL percentages are a red flag — it means your agent is on autopilot, not thinking. ### 1. Setup ./skills/sightglass/setup.sh This installs the CLI (@sightglass/cli), runs initial configuration, and checks the watcher daemon. ### 2. Login sightglass login Authenticate with sightglass.dev to enable cloud analysis and history. ### 3. Watch sightglass watch Starts the background watcher that monitors agent sessions — file changes, package installs, tool calls. ### 4. Analyze sightglass analyze # or ./skills/sightglass/analyze.sh --since "1 hour ago" --format json ### Automatic Session Tracking Sightglass provides pre/post hooks for coding agent sessions: Before a session — hooks/pre-spawn.sh: Records start time and project context Ensures the watcher daemon is running After a session — hooks/post-session.sh: Runs analysis on everything that happened Outputs a summary: risks found, training recall %, alternatives missed ### Using with a Coding Agent When you spawn a coding agent through OpenClaw, wrap it with Sightglass: # Before spawning source ./skills/sightglass/hooks/pre-spawn.sh /path/to/project # ... agent does its work ... # After session ends ./skills/sightglass/hooks/post-session.sh The post-session output looks like: 📊 Session Summary Dependencies added: 12 Risks found: 3 Training recall: 67% Alternatives missed: 5 ⚠️ Run 'sightglass analyze --since ...' for details 67% training recall means two-thirds of the packages were grabbed from memory with zero comparison shopping. Sightglass will show you what alternatives existed. ### CLI (@sightglass/cli) CommandDescriptionsightglass initInitialize Sightglass in a project directorysightglass loginAuthenticate with sightglass.devsightglass setupInteractive first-time configurationsightglass watchStart the watcher daemonsightglass analyzeAnalyze agent sessions and dependency decisions ### Skill Scripts ScriptDescriptionsetup.shInstall CLI, configure, verify watcheranalyze.shStandalone analysis with --since, --session, --format, --push flagshooks/pre-spawn.shPre-session hook — records start, ensures watcherhooks/post-session.shPost-session hook — analyzes and summarizes ### analyze.sh Flags --since