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 timseriakov/sem-inspect-weave-skill --skill sem-inspect-weavegit clone --depth 1 https://github.com/timseriakov/sem-inspect-weave-skillWrote 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/timseriakov/sem-inspect-weave-skill/sem-inspect-weave)<a href="https://agentmods.dev/skills/timseriakov/sem-inspect-weave-skill/sem-inspect-weave"><img src="https://agentmods.dev/badge/skills/timseriakov/sem-inspect-weave-skill/sem-inspect-weave/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/timseriakov/sem-inspect-weave-skill/sem-inspect-weave"><img src="https://agentmods.dev/badge/skills/timseriakov/sem-inspect-weave-skill/sem-inspect-weave.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 | $0.00033 | $0.00652 |
| Opus 5 | $0.00016 | $0.00326 |
| Sonnet 5 | $0.00007 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
sem-inspect-weave 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 12d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sem / Inspect / Weave
This skill teaches a single coherent workflow:
sem -> inspect -> weave
Use it when you need entity-level understanding (functions/classes/properties), risk-focused review prioritization, and safe merge/coordination semantics.
When to Use
- Semantic or entity-level diff analysis (not just line diffs)
- Impact questions (what else breaks if this entity changes?)
- Risk triage (what deserves careful review first?)
- Branch integration prep / semantic conflict analysis
- Multi-agent overlap (avoid false conflicts)
When Not to Use
- Trivial changes where direct reading is cheaper
- Any workflow that would mutate repo merge configuration by default
Reasoning Model
- Discover changes -> sem
- Understand impact -> sem impact / sem graph / sem blame
- Prioritize review -> inspect
- Coordination + merge semantics -> weave
Tool Roles
| Tool | Core Role | Notes |
|---|---|---|
sem |
structural truth | Entity-level diff/graph/impact/blame. Establishes what changed. |
inspect |
review prioritization | Classifies + risk-scores entities (blast radius, dependents, public API) and groups changes for review order. |
weave |
coordination + merge semantics | Entity-level merge semantics and optional advisory coordination (claims). |
Trigger Phrases
- semantic diff
- entity-level diff
- use sem to analyze changes
- review this change semantically
- analyze impact of this change
- find risky entities in this diff
- prioritize review for this commit
- prepare safe merge
- detect semantic conflicts
Typical Workflows
Review last commit
What ships with it
11 files 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.
- agents/openai.yaml 270 B
- references/commands.md 734 B
- references/decision-guide.md 492 B
- references/examples.md 446 B
- references/inspect-risk-model.md 428 B
- references/limitations.md 402 B
- references/weave-coordination.md 610 B
- scripts/inspect-review-target 947 B
- scripts/sem-json 735 B
- scripts/skill-preflight 3.1 KB
- scripts/weave-preview-safe 227 B
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.
- 12d ago First seen · 106 lines · 33 tokens per session scan A a6fb4923dfb7
sem-inspect-weave is a skill published in the GitHub repository timseriakov/sem-inspect-weave-skill (3 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 652 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 2026-08-31.
Other skills, from other repositories
resolve-pr-comments
This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".
review-pr
This skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this PR", "check PR.
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
gitlab-create-mr
Create GitLab merge requests from a local branch using a reviewable workflow for branch checks, GitLab host detection, diff analysis, title and description writing, and glab mr create. Use when opening a GitLab merge request, drafting or improving merge request copy, preparing a branch for review, or working across…
code-review
Request or perform a git-backed code review for a defined diff or SHA range using implementation context and requirements. Use when finishing a task, completing a major feature, preparing to merge, or when you need a fresh review before proceeding.