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/ignaciomarin402/spec-flow-plugin/spec-flow-setupnpx skills add IgnacioMarin402/spec-flow-plugin --skill spec-flow-setupgit clone --depth 1 https://github.com/IgnacioMarin402/spec-flow-pluginWrote 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/ignaciomarin402/spec-flow-plugin/spec-flow-setup)<a href="https://agentmods.dev/skills/ignaciomarin402/spec-flow-plugin/spec-flow-setup"><img src="https://agentmods.dev/badge/skills/ignaciomarin402/spec-flow-plugin/spec-flow-setup.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 | $0.00096 | $0.01651 |
| Opus 5 | $0.00048 | $0.00826 |
| Sonnet 5 | $0.00019 | $0.00330 |
| Haiku 4.5 | $0.00010 | $0.00165 |
Grade A, and why
spec-flow-setup 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting up the contract
init reads what a repo declares about itself and refuses to invent the rest.
For a repo whose manifest declares its commands that is nearly the whole job;
for every other repo it reports a list and stops. You are the second half:
you supply what the repo did not declare, and then you prove the result rather
than announcing it.
Two rules govern everything below, and they are the reason this is a skill and not a script (see ADR-006):
- Never write a value you did not read or verify. A field filled with a
plausible guess is worse than the
MISSINGline it replaced — that line was honest. - You are not the check. Nothing you conclude counts until
check-changed.mjsexits 0. Your last action is running it and quoting what it said.
1. Ask the engine first
node ${CLAUDE_PLUGIN_ROOT}/scripts/init.mjs
If .spec-flow/config.json already exists, do not re-run this with
--force — that is for a repo whose contract you mean to regenerate. Read the
existing file and go to step 4; you are repairing, not adopting.
init sorts every field into detected, REVIEW or MISSING, and exits
non-zero while anything is missing. That output is your worklist. Nothing else
is.
2. Fill what it could not read
For each MISSING field, find what the repo already declares — its manifest,
its linter's configuration file, the directory its tests live in, the naming
its test files follow. Read those files. If a field cannot be determined from
anything in the repo, ask the user; do not pick a default.
REVIEW lines are inferences the engine made and wants confirmed. Confirm them
against the repo, and correct the ones that are wrong.
Two that are worth extra care because a wrong value is quiet rather than loud:
- the lint command must take file paths appended to it. The gate appends the changed files itself. A command with a target already in it lints the whole repo on every gate, which undoes the scoping that keeps a milestone from being blocked by debt it never touched.
proof_dirandproof_suffixare where agents PUT new tests. They no longer decide what counts as proof, so a wrong value costs consistency rather than a blocked gate — which is exactly why nothing will tell you it is wrong.
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 · 148 lines · 96 tokens per session scan A d13207d59d6e
spec-flow-setup is a skill published in the GitHub repository IgnacioMarin402/spec-flow-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 1,651 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
pm
Project manager for GitHub issues: brainstorm design approaches, create structured issues optimized for LLM agent teams, triage and recommend what to work on next, audit and clean up stale issues, or deep-validate a single issue against the codebase. Triggers: create issue, plan work, new task, project manager, write…
skill-creation
Use when creating a new skill, improving an existing skill, or deciding what a skill should contain and how it should be structured.
quest
Use for any non-trivial task. Orchestrates the Research-Plan-Implement cycle with compaction between phases, integrating council, lembas, gather-lore, and warden. Enforces discipline and phase gates.
lat-code
Execute one approved code-phase task from .lat/workspace/ /tasks.yaml as the codeexecutor, persist its result and lifecycle status without deleting history, then exit. Use when the prompt contains lat-code or names a LAT TASKID ledger with a codeexecutor agentid. Typically launched by lat-dispatch.
pb-injury
Log and manage an injury — track the episode, stage the return-to-run, and guardrail the plan.
gaia-compact
Use when the user asks to compact the current session, including “compacta”, “compactemos”, or “compact the session”.