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/sdfdu/evopilot/dev-flownpx skills add sdfdu/evopilot --skill dev-flowgit clone --depth 1 https://github.com/sdfdu/evopilotWhat 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 | $0.00034 | $0.00211 |
| Opus 5 | $0.00017 | $0.00105 |
| Sonnet 5 | $0.00007 | $0.00042 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
dev-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 yesterday.
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.
What it actually says
Dev Flow
Load relevant EvoPilot context before choosing a workflow. Explicit task and repository instructions override memory.
- Inspect the smallest relevant project surface and preserve unrelated user changes.
- Make reasonable low-risk implementation decisions autonomously.
- Validate in proportion to risk: targeted checks first, broader checks when warranted.
- Use
evopilot_observeto record the workflow category and outcome, not raw source, secrets, or terminal output. - Record a preference only when explicit or supported by repeated evidence.
- On repeated failures, try safe alternatives with a bounded stopping condition; then report the actual blocker.
- Before external publication, destructive operations, credential use, or system-wide changes, call
evopilot_review_actionand require a person when directed.
Finish with the outcome, verification, and one evidence-based learning note when something durable was learned.
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.
- yesterday First seen · 19 lines · 34 tokens per session scan A 1986e9c9fabd
dev-flow is a skill published in the GitHub repository sdfdu/evopilot (2 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 211 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 2026-08-31.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
debugging-mutations
Verify what changed on a ServiceNow instance after a tool call — sysaudit inspection, syslog/transaction logs, session context, Flow Designer execution logs, outbound HTTP traces.
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).