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 ambient-code/platform --skill devflowgit clone --depth 1 https://github.com/ambient-code/platformWrote 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/ambient-code/platform/devflow)<a href="https://agentmods.dev/skills/ambient-code/platform/devflow"><img src="https://agentmods.dev/badge/skills/ambient-code/platform/devflow/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/ambient-code/platform/devflow"><img src="https://agentmods.dev/badge/skills/ambient-code/platform/devflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 6 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Privilege Escalation · line 273 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- high Tool Misuse · line 338 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Agent Snooping · line 26 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 191 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 243 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00060 | $0.03152 |
| Opus 5.5 | $0.00024 | $0.01261 |
| Sonnet 5.5 | $0.00012 | $0.00630 |
| Haiku 4.5 | $0.00006 | $0.00315 |
Grade A, and why
devflow 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 1mo 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devflow Skill
You are executing the Ambient Code Platform development workflow. This skill is the literal sequence of steps performed every time code is changed — from filing a ticket to verifying a deployment.
Self-improving skill. Whenever you discover something that doesn't work, or discover something that does, update this file immediately before moving on. The next invocation of this skill benefits from every correction. Examples of self-improvement triggers:
- A build command fails and you find the right flags → add them here
- A test requires an env var you didn't know about → add it here
- A path you tried is a dead end → document the dead end and the correct path
- A review comment reveals a missing step → add the step here
Turn Counter
Remind the human every 10 turns to re-read this skill. Context compaction can lose workflow state. At turns 10, 20, 30, etc., say:
"Reminder: we are on turn N. Re-reading
skills/devflow/SKILL.mdto refresh workflow state."
Then re-read this file before continuing.
Workflow Overview
1. Ticket (optional)
2. Branch (from ticket name if available)
3. Spec change (load + modify the component's .spec.md)
4. Commit spec → push → PR against `main`
5. Review (agentic: thorough PR review; human: desired but optional)
6. On spec acceptance → load the component's .guide.md (the implementation workflow)
7. Branch (from ticket name if available)
8. Commit order:
a. Guide/skill/workflow self-improvement changes (1 commit)
b. Code changes grouped by component
9. Push → PR against `main`
10. Review (human + bot comments; local review too)
11. On merge → await quay.io image
12. Update gitops repository with new image SHA (Skill TBD)
13. After deployment → run tests / e2e suite (TBD)
Phase 1: Ticket & Branch
1a. File a Ticket (optional)
If there is a Jira or GitHub issue, note the ticket ID. If not, proceed without one.
1b. Create a Branch
# With ticket
git checkout -b <ticket-id>/<short-description>
# Without ticket
git checkout -b <type>/<short-description>
# type: feat, fix, refactor, docs, chore
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.
- 1mo ago First seen · 375 lines · 60 tokens per session scan A 0c2dd0c41fc5
devflow is a skill published in the GitHub repository ambient-code/platform (131 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 3,152 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 2026-08-30.
Other skills, from other repositories
conventional-commit
Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.
01-commit
Create atomic conventional commits; safely retry scoped hook fixes; optionally push. Use when the user wants to commit changes, optionally pushing the branch. Not for amending, rebasing, opening a pull request, or tagging a release.
teamserver-git
Commit, branch and push a Mendix project in git the way Studio Pro and Mendix Team Server expect — branches created on the server (not with git checkout -b), the mxmetadata commit note written with mxcli git note, and the notes ref pushed with the branch. Use before any git commit, branch, merge, rebase or push in a…
review
Use when operating as the Fabrik Review stage agent. This skill guides code review of an implementation, finding and fixing issues, and ensuring the PR is ready for human review.
implement
Use when operating as the Fabrik Implement stage agent. This skill guides the implementation of a planned feature, following the task checklist to produce committed, tested, pushed code on a feature branch.
review-comment
Use when operating as the Fabrik Review comment reviewer. This skill guides applying user decisions on review findings — fixing issues, dismissing false positives, or deferring items — then committing and pushing without signaling stage completion.