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 inspecto-dev/inspecto --skill inspecto-onboarding-traegit clone --depth 1 https://github.com/inspecto-dev/inspectoWrote 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/inspecto-dev/inspecto/inspecto-onboarding-trae)<a href="https://agentmods.dev/skills/inspecto-dev/inspecto/inspecto-onboarding-trae"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/inspecto-onboarding-trae/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/inspecto-dev/inspecto/inspecto-onboarding-trae"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/inspecto-onboarding-trae.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.01216 |
| Opus 5 | $0.00020 | $0.00608 |
| Sonnet 5 | $0.00008 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00122 |
Grade A, and why
inspecto-onboarding 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 9d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspecto Onboarding
Use this as a compatibility instruction for Trae IDE and Trae CLI agent runtimes. Use Inspecto's structured CLI flow instead of hand-editing project files. Always prefer the single-entry onboarding command.
Workflow
- Execute the Inspecto CLI to get the JSON plan.
- Run
scripts/run-inspecto.sh onboard --json. - The launcher already prefers
INSPECTO_CLI_BIN,INSPECTO_DEV_REPO, a locally availableinspectoexecutable, and only falls back to@latestas the last resort.
- Run
- If the result returns
status: "needs_target_selection", explain that this step chooses which local development build target should receive the Inspecto plugin and settings. Show the targetcandidates, prefer each candidate'scandidateId, ask the user which exact candidate to use, then rerun with--target <candidateId>. The CLI also accepts a returnedconfigPathas a compatibility fallback. Do not collapse the user's choice back to a package path when the same package has multiple build configs.- If the user names a config file that is not present in the returned
candidates, stop and explain that Inspecto did not recognize that config as a valid onboarding target. Do not force the target, do not guess another value, and do not begin manual config edits unless the user explicitly asks for a manual fallback.
- If the user names a config file that is not present in the returned
- If the result returns
status: "needs_confirmation", summarizesummary.headline,summary.changes,summary.risks, andsummary.manualFollowUp, then ask for approval before rerunning with--yes. - If the user explicitly asked to see the plan before any changes, stop after the
needs_confirmationsummary and wait for approval. - If the result returns
status: "partial_success"anddiagnostics.nextStepsincludes IDE extension installation, treat that as a blocking onboarding follow-up. Do not move on to dev-server validation until the extension is installed automatically or the user confirms they completed the manual install. - When manual IDE extension installation is needed, guide the user to search "Inspecto" in the Trae Extension Marketplace and install it.
- If the result returns
status: "error", summarizediagnostics.errorsanddiagnostics.nextSteps. Runscripts/run-inspecto.sh doctor --jsononly when explicit recovery diagnostics are still needed. - Only after the IDE extension step is complete, read the onboarding result's
verificationfield. - If
verification.availableistrueandverification.devCommandis present, offer to start that exact command immediately for validation. - Otherwise, use
verification.messageand tell the user to start their normal dev server command manually. - If the result includes
handoff.patches, treat those patches as the primary source of truth for any remaining manual work. Apply the generated patches directly before exploring external docs or unrelated files. - Only fall back to extra documentation or broader repo exploration when a returned patch is clearly insufficient or conflicts with the local project structure.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 64 lines · 40 tokens per session scan A 93440b043e1a
inspecto-onboarding is a skill published in the GitHub repository inspecto-dev/inspecto (23 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 1,216 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
post-mortem
Diagnose instruction defects and optionally submit Rosetta GitHub issue.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
solr-query
To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.