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 SNIKO/agent-skills --skill swe-shapegit clone --depth 1 https://github.com/SNIKO/agent-skillsWrote 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/sniko/agent-skills/swe-shape)<a href="https://agentmods.dev/skills/sniko/agent-skills/swe-shape"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/swe-shape/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/sniko/agent-skills/swe-shape"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/swe-shape.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 | $0.00038 | $0.01894 |
| Opus 5.5 | $0.00015 | $0.00758 |
| Sonnet 5.5 | $0.00008 | $0.00379 |
| Haiku 4.5 | $0.00004 | $0.00189 |
Grade A, and why
swe-shape 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline
swe-shape → swe-spec → [swe-plan] → [swe-worktree] → swe-execute → swe-review, with swe-research available at any point.
Each stage runs in its own session: the user invokes one skill, reviews the artifact, clears the context, then invokes the next with the artifacts as input. Assume no memory of other stages beyond the files named below.
- This stage: decide whether the idea is worth building and what it must achieve.
- Reads: the user's idea, the repository, and the shared research corpus.
- Writes:
brief.md. - Next: the user runs
swe-specto decide what actually changes.
Purpose
Determine whether a proposed change is worth building, what outcome it must produce, and whether it is feasible in this repository. Produce a brief — not a design, at any level of detail.
Inputs
CHANGE_DIR: .swe/YYYY-MM-DD-<slug>/ — create it for this change unless the conversation already names one.
BRIEF_FILE: {CHANGE_DIR}/brief.md, written from brief.template.md.
RESEARCH_DIR: .swe/research/ — shared across all changes, indexed by INDEX.md.
What Belongs in a Brief
A brief answers why, and how will we know it worked. It never says how the change is built.
The working test: every statement in the brief must still be true if the codebase were rewritten from scratch in a different language. If a statement would change because the implementation changed, it belongs to the next stage.
- "p95 under 300ms" belongs. "Response cached in Redis with a 60s TTL" does not.
- "Must not break the v1 API contract" belongs. "The v1 adapter maps
footobar" does not. - "Must reuse the existing job queue" does not — that is a solution choice. If it is genuinely non-negotiable for an external reason, record the reason in Non-negotiables, not the mechanism.
Engineering Stance
You and the user are peers shaping this idea together; neither outranks the other, and being asked to put something in the brief is not authorization to record it unexamined.
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.
- 1mo ago First seen · 118 lines · 38 tokens per session scan A d6c32bf513bd
swe-shape is a skill published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,894 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
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for publishartifact, outputiframe, or slackattachhtml.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
workspaces
How an Open SWE workspace's sandbox image works and how to change it — create one, edit or fork an existing one, start from scratch, what setupscript and updatescript are for, why a nightly refresh failed, where the build logs are, and how to read a rebuild in progress. Read this whenever someone asks about…
linear-tickets
Create or update high-quality Linear tickets while preserving the originating report, diagnostic links, attachments, and reporter/requester attribution. Read this whenever someone asks to create, recreate, or update a Linear issue.
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.
oracle-advisor
Request a second-model consultation with explicit API, browser, or render transport and per-run provenance. Use when transport choice or model/effort evidence is part of the request; the existing oracle skill remains the browser-first workflow.