oneshot

oneshot is a skill for Claude Code, Codex from fall-out-bug/sdp. It costs 14 tokens per session (952 once invoked), scanned A, original, MIT.

An automation loop for carrying out a planned software feature through build, review, and automated checks. It uses SDP Orchestrate to track the workstream and its current phase.

In plain words
What is it for?
Use it to run the next build or review action, advance the tracked phase, fix review problems, and finish when continuous integration is green.
Why use it?
It keeps feature execution in a controlled sequence and prevents the work from quietly expanding beyond its agreed scope.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fall-out-bug/sdp/oneshot
Any agent
npx skills add fall-out-bug/sdp --skill oneshot
Clone the repo
git clone --depth 1 https://github.com/fall-out-bug/sdp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for oneshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/fall-out-bug/sdp/oneshot.svg)](https://agentmods.dev/skills/fall-out-bug/sdp/oneshot)
Your own site
<a href="https://agentmods.dev/skills/fall-out-bug/sdp/oneshot"><img src="https://agentmods.dev/badge/skills/fall-out-bug/sdp/oneshot.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 952 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00952
Opus 5 $0.00007 $0.00476
Sonnet 5 $0.00003 $0.00190
Haiku 4.5 $0.00001 $0.00095

Measured 3d ago against content hash 736087620acb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oneshot 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 3d 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.

prompts/skills/oneshot/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oneshot

Outer loop: sdp-orchestrate (or sdp orchestrate if available) drives phases. You execute @build and @review inline.

Run orchestrate: Either sdp-orchestrate on PATH, or from project root: go run ./cmd/sdp-orchestrate. See AGENTS.md for build/install.

Rules

  1. Scope — Do not change workstream scope mid-run. If scope must change, stop and start a new run.
  2. Get next action — Run sdp-orchestrate --feature F{XX} --next-action. Parse the JSON output (schema: sdp/schema/next-action.schema.json).
  3. Execute phase and advance — For build: run @build {ws_id}, commit, then sdp-orchestrate --feature F{XX} --advance --result $(git rev-parse HEAD). For review: run @review F{XX}, fix P0/P1 until approved (max 3 iterations), then sdp-orchestrate --feature F{XX} --advance. One advance per phase — run --advance exactly once after build, exactly once after review. PR and CI run automatically. When action is done, output only: CI GREEN - @oneshot complete.

Post-compaction

If context was compacted, read .sdp/checkpoints/F{XX}.json and git checkout $(jq -r .branch .sdp/checkpoints/F{XX}.json). Resume from step 1.

Write Plan (F101)

Before the orchestration loop begins, emit a write plan for orchestrator-owned artifacts. @build and @review emit their own detailed file plans when invoked:

  1. Enumerate — List every file the skill will CREATE / MODIFY / DELETE with a one-line reason. Covers .sdp/checkpoints, .sdp/evidence, .sdp/ws-verdicts, and orchestrator state files. @build and @review handle their own file plans.
  2. Flags:
    • --dry-run — Emit write plan only. Do NOT create, modify, or delete any file.
    • --yes — Skip confirmation prompt. Execute immediately. Intended for CI/non-interactive.
  3. Confirm — Present the plan to the user and wait for explicit approval (unless --yes).
  4. Log — Append write plan event to .sdp/log/events.jsonl (sanitize file paths before logging: strip newlines, ensure valid JSON escaping):
    {"spec_version":"v1.0","event_id":"<uuid>","timestamp":"<ISO-8601>","source":{"system":"sdp-lab","component":"oneshot"},"event_type":"decision.made","payload":{"decision_type":"write_plan","plan":[{"path":"...","action":"CREATE|MODIFY|DELETE","reason":"..."}]},"context":{"feature_id":"<F-id if known>","workstream_id":"<ws-id if applicable>"}}
    
    Include context fields only when the ID is known at plan time. Omit unavailable fields rather than inventing placeholders.

    Note: Phase 1 uses prompt-level write boundaries (CLI out of scope). Aligns with sdp/schema/contracts/orchestration-event.schema.json via event_type: "decision.made". Phase 2 CLI will emit natively.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 3d ago First seen · 62 lines · 14 tokens per session scan A 736087620acb

Subscribe to this mod's changes

oneshot is a skill published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 952 once invoked, about $0.0001 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.