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 pwdev-solucoes/pwdev-claude-marketplace --skill flow-executegit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/flow-execute)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-execute"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-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 5.1 | $0.00045 | $0.00489 |
| Opus 5 | $0.00023 | $0.00244 |
| Sonnet 5 | $0.00009 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
flow-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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute approved tasks
Read execution, planning, collaboration, memory, artifacts, and safety.
Entry gate
Require an approved plan, satisfied dependencies, and identifiable verification commands. Stop if the plan is stale, contradicts the specification, or overlaps unrelated user changes unsafely.
Procedure
- Execute inline by default. Select one ready task; do not mix tasks or waves in one implementation unit.
- Read the full task, linked specification clauses, required context, applicable instructions, relevant memory, and current Git status.
- Confirm allowed files and state the task contract before editing.
- For behavior changes, write the focused failing test first and observe the expected failure.
- Implement only the approved actions with the smallest sufficient change.
- Run focused verification, then the relevant broader suite.
- Inspect the complete diff for scope, correctness, safety, and prohibited behavior.
- Write the execution summary specified by execution and update state only from fresh evidence.
- Continue to the next ready task only when the current result is
COMPLETEor an acceptedCAVEATS. - After all tasks, set
REVIEW_REQUIREDand recommend$flow-simplifyor$flow-review.
Blockers and corrections
On NEEDS_ADVICE, stop edits, persist the structured question, and request one decision. For fix plans, follow the same lifecycle and enforce the maximum correction cycles. Never silently redesign scope.
Collaboration and Git
Use collaborating workers only when the user explicitly requests delegation or parallel agent work. Never assign overlapping writers and independently verify returned claims.
Do not commit, push, create a branch, clean files, or rewrite history unless the user explicitly authorizes that exact action. Leave the diff reviewable.
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 · 40 lines · 45 tokens per session scan A b458b8b251b6
flow-execute is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 489 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
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.