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 me-cedric/agent-compass --skill spec-flowgit clone --depth 1 https://github.com/me-cedric/agent-compassWrote 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/me-cedric/agent-compass/spec-flow)<a href="https://agentmods.dev/skills/me-cedric/agent-compass/spec-flow"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/spec-flow/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/me-cedric/agent-compass/spec-flow"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/spec-flow.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 | $0.00043 | $0.01241 |
| Opus 5.5 | $0.00017 | $0.00496 |
| Sonnet 5.5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
spec-flow 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-flow
Use the smallest spec that prevents a misunderstanding. A tiny edit needs only an inline brief: goal, non-goal, acceptance, validation.
Layout
OpenSpec lives in {{OPENSPEC_DIR}}. The schema is konvoy-delivery.
{{OPENSPEC_DIR}}/constitution.md
{{OPENSPEC_DIR}}/changes/<id>/proposal.md
{{OPENSPEC_DIR}}/changes/<id>/specs/<cap>/{spec,plan,checklist,tasks}.md
{{OPENSPEC_DIR}}/changes/archive/
Flow
- Proposal: write what and why. Do not name a stack. Start with
openspec new change <id>. - Clarify: ask until no high-impact
[NEEDS CLARIFICATION]remains. Usegrillfor a long interview. - Specs: fill the headings of the schema template. Then append the delta section. See
references/delta-section.md. - Plan and tasks: write ordered tasks, tests first. Mark parallel-safe tasks with
[P]. - Apply: implement only after the spec, plan and tasks are stable.
- Validate, then archive.
openspec status --change <id> --json
openspec instructions apply --change <id> --json
openspec validate --all --strict --json
openspec archive <id>
Read status before each step. Do not guess which artifact is ready.
Run validate before you report done. Run archive only when the user asks.
Run ac check --docs before you report done. It checks the RAID files, the ADRs and the screen tags.
It also runs openspec validate when the CLI is installed.
Init from specs
Use this to start a project from input documents: a brief, a tender, meeting notes.
- Run
ac init --from-specs <dir>. It creates the layout and copies the documents into{{OPENSPEC_DIR}}/inbox/<dir name>/. - Convert each document that is not Markdown. See
references/convert-documents.md. - Run
grillon the inbox. It writes one RAID file for each open question. - Write
{{OPENSPEC_DIR}}/constitution.mdif it does not exist. Ask for the governing rules. Do not invent them. - Write one change for each feature: the proposal first, then the quartet for each capability.
- Keep the inbox files. They are the source of each requirement.
What ships with it
4 files 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.
- 9d ago Changed · -3 tokens per session 2591444c10f2
- 10d ago First seen · 113 lines · 46 tokens per session scan A fdb922a79ac6
spec-flow is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 1,241 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.