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 agentmods add skills/sniko/agent-skills/swe-executenpx skills add SNIKO/agent-skills --skill swe-executegit 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-execute)<a href="https://agentmods.dev/skills/sniko/agent-skills/swe-execute"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/swe-execute.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.01974 |
| Opus 5 | $0.00025 | $0.00987 |
| Sonnet 5 | $0.00010 | $0.00395 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade A, and why
swe-execute 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 4d 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 — 146 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 result, clears the context, then invokes the next. Assume no memory of other stages beyond the files named below.
- This stage: implement the remaining slices, one fresh sub-agent per slice, and verify each.
- Reads:
spec.html(the approved design and contracts, written byswe-spec),brief.mdacceptance criteria (written byswe-shape),plan.mdwhen one exists (slice ordering, written byswe-plan), andstate.md(progress from earlier execution sessions). - Writes:
state.md. Sub-agents write production code and tests. - Next: the user runs
swe-reviewin a fresh session.
Purpose
Act as the execution orchestrator: select slices in order, brief a fresh sub-agent for each one, confirm its work against the authoritative artifacts, record progress, and stop the run rather than let any slice silently diverge from the spec.
Your own context stays small and durable. Implementation context is disposable and lives in the sub-agents.
Inputs and Workspace
CHANGE_DIR:.swe/<change>/— infer only when unambiguous.SPEC_FILE:{CHANGE_DIR}/spec.html— canonical contract, at whatever depth each section reached. Read its table of contents and load only the sections a slice touches.{CHANGE_DIR}/plan.md— slice list and order when it exists; otherwise treat the spec as one slice.{CHANGE_DIR}/state.md— created from state.template.md when implementation starts. You are its only writer.RESEARCH_DIR:.swe/research/— shared corpus, indexed byINDEX.md.
Work in the user-selected branch or worktree and preserve unrelated changes.
Delegation Model
One sub-agent per slice, with a fresh context, dispatched sequentially. Never run two slices concurrently: they share a working tree.
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.
- 4d ago First seen · 146 lines · 50 tokens per session scan A 3c1444731125
swe-execute is a skill published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 1,974 once invoked, about $0.0003 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
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 saveplan, outputiframe, or slackattachhtml.
bootstrap-repo-analysis
First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
write-oep
Draft an Open SWE Enhancement Proposal using the repository's OEP process and template. Use when the user asks to create, write, or propose an OEP or invokes /write-oep.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.