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 commands/fall-out-bug/sdp/oneshotgit clone --depth 1 https://github.com/fall-out-bug/sdpWhat 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 | $0.00013 | $0.00267 |
| Opus 5 | $0.00006 | $0.00133 |
| Sonnet 5 | $0.00003 | $0.00053 |
| Haiku 4.5 | $0.00001 | $0.00027 |
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 2d 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.
What it actually says
/oneshot — Autonomous Feature Execution
When calling /oneshot F{XX} in Cursor:
- Load skill:
@.claude/skills/oneshot/SKILL.md - Run
sdp-orchestrate --feature F{XX} --next-actionas the outer loop - Execute each phase inline:
- build: @build {ws_id} → commit →
sdp-orchestrate --feature F{XX} --advance --result <commit> - review: @review F{XX} → fix P0/P1 →
sdp-orchestrate --feature F{XX} --advance
- build: @build {ws_id} → commit →
- PR creation and CI loop are handled by the CLI — no agent involvement
- When done: output only
CI GREEN - @oneshot complete
Input: Feature ID (from @feature or ROADMAP) Output: All WS executed + CI green. No "Next steps" or handoff lists.
opencode: Use sdp-orchestrate --feature F{XX} --runtime opencode as the outer loop. opencode lacks Stop hooks — the outer loop CLI replaces them.
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.
- 2d ago First seen · 22 lines · 13 tokens per session scan A a6725649f54f
oneshot is a command published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 267 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.
Other commands, from other repositories
tdd-workflow
Implement the behavior described in $ARGUMENTS using strict TDD. Follow this exact sequence. Do not collapse phases. Each gate requires actual test runner output.
api-add-endpoint
Create a new API endpoint. $ARGUMENTS should describe the endpoint (e.g., "POST /api/users - create a user").
code-review
Review the code changes in this project. For each file changed.
refactor-file
Refactor the file specified in $ARGUMENTS following project conventions.
api-test-endpoint
Test the API endpoint specified in $ARGUMENTS.
debug-error
Debug the following error. $ARGUMENTS should contain the error message or stack trace.