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/boshu2/agentops/scaffoldnpx skills add boshu2/agentops --skill scaffoldgit clone --depth 1 https://github.com/boshu2/agentopsWhat 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 | $0.00035 | $0.00784 |
| Opus 5 | $0.00017 | $0.00392 |
| Sonnet 5 | $0.00007 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
scaffold 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold
Create one bounded project, component, or CI scaffold. This specialist does not schedule RPI, create work ownership, mutate Git, or decide what happens next.
Contract
- Resolve the requested target root and declare the exact paths that may be created or changed.
- Refuse to overwrite an existing path without explicit caller authorization.
- Generate idiomatic, functional files with at least one behavioral test for generated behavior.
- Run the target's selected build, test, and lint commands once.
- Report the files changed and factual command results, then stop.
Use the current agent and local shell unless the caller explicitly requests a different runtime. Preserve unrelated existing changes.
Clone a proven exemplar
Before inventing structure, find one working exemplar — an existing project, component, or CI file in this repository or the target's ecosystem that already builds, tests, and ships — and clone its shape, renaming and pruning to the request. Invent structure only where no exemplar exists, and say so in the report. Designing a novel layout when a proven one was available is the blank-page scaffold failure mode: every invented convention is an unreviewed decision the target team now owns. Stop condition: if two candidate exemplars disagree on a structural choice, pick the one whose verification commands pass today and record the choice; do not blend both.
One source of truth, one-way sync
When the scaffold contains derived or duplicated content (generated config, mirrored constants, templated CI matrices), designate exactly one source of truth and make every copy flow from it in one direction, atomically — a single regeneration step produces all copies, and hand-editing a copy is defined as wrong by the scaffold's own docs or checks. Two files that must be edited in tandem by memory are the twin-edit trap failure mode; a scaffold that ships one is incomplete. If the request forces bidirectional sync, stop and report the conflict instead of scaffolding it.
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.
- 3d ago First seen · 98 lines · 35 tokens per session scan A a3313f1001e0
scaffold is a skill published in the GitHub repository boshu2/agentops (431 stars, last pushed 5d ago), licensed Apache-2.0. It adds 35 tokens to every session and 784 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 2026-08-30.
Other skills, from other repositories
brainstorm
Explore vague or ambitious ideas into a right-sized requirements-only plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning, not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or…
doc-review
Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.
doubt-driven
Doubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes are high, a claim can't be checked by the type system or compiler, or verifying now is cheaper than debugging later.
drift-detect
Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project. For doc-vs-code drift inside a specific diff, use sync-docs.