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 marchatton/agent-skills --skill wf-developgit clone --depth 1 https://github.com/marchatton/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/marchatton/agent-skills/wf-develop)<a href="https://agentmods.dev/skills/marchatton/agent-skills/wf-develop"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/wf-develop/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/marchatton/agent-skills/wf-develop"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/wf-develop.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 | $0.00817 |
| Opus 5 | $0.00019 | $0.00409 |
| Sonnet 5 | $0.00008 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
wf-develop 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 7d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wf-develop
Purpose
Implement changes with a verification-first loop, keeping context clean between workflow steps.
prd.json (single-PRD dossier or slice PRD).
plan.md may exist for higher-risk work, but it’s optional.
Prefer plan-driven work when plan.md exists, but allow PRD-driven work (especially with PRD JSON: prd.json).
Inputs
Preferred:
- Dossier path (contains one or more
prd.json) - implement oneprd.jsonat a time. - Or explicit PRD JSON path (
prd.json/prds/<slice_id>_<slug>/prd.json)
Optional:
plan.mdpath (only when created by wf-plan)
Also:
- Target repo + branch
- Known risks/deps
Outputs
- Code changes
- Verification evidence (what ran, result, screenshots/logs when relevant)
- Update the relevant PRD JSON story
passesandnotesto reflect reality (prd.jsonor a sliceprds/.../prd.json) - Dev log artefact saved per repo conventions (summary + verification evidence + GO/NO-GO) (optional but nice)
Steps
- (Recommended) Pickup if starting fresh thread / resuming
- Invoke
pickupskill if:- new chat/thread, or
- user says “resume / pick up”, or
- repo/branch uncertain
- Confirm work input
- If PRD JSON missing (
prd.json): check ifprd.mdexists. If yes, runcreate-json-prdfirst (NO-GO if schema invalid). If not, ask user to createprd.md. - If
plan.mdexists: use it in conjunction withprd.jsonto guide development. - If no plan.md: proceed from the
prd.jsondirectly (this is normal for small work).
- Baseline verification (before touching code)
- Run verify skill and record result.
- If verify fails before changes:
- call out as pre-existing failure
- ask whether to fix baseline first (recommended) or continue
- Implement in smallest verifiable increments Loop:
- pick the next smallest slice that proves progress toward an acceptance criterion
- implement minimal change
- run targeted check then verify skill
- record evidence (what ran, result, any screenshots/logs)
- update the relevant PRD JSON:
- set
passes=truefor stories fully meeting criteria - use
notesfor partials, tradeoffs, follow-ups
- set
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.
- 7d ago First seen · 97 lines · 38 tokens per session scan A f43cd597bd20
wf-develop is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 817 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 2026-09-03.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.