Borrowing it
Nothing to install: this file belongs to adrienm7/ergopti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adrienm7/ergopti/main/.agents/skills/workflow-change-control/SKILL.mdgit clone --depth 1 https://github.com/adrienm7/ergoptiWrote 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/adrienm7/ergopti/workflow-change-control)<a href="https://agentmods.dev/skills/adrienm7/ergopti/workflow-change-control"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/workflow-change-control/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/adrienm7/ergopti/workflow-change-control"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/workflow-change-control.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 | $0.00042 | $0.00807 |
| Opus 5.5 | $0.00017 | $0.00323 |
| Sonnet 5.5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
workflow-change-control 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 15d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changing requirements while a workflow runs
A running workflow holds agent context that no file preserves. Stopping it
destroys the context of every agent in flight; only their commits and file edits
survive. Resuming replays from cache only the longest unchanged prefix of
agent() calls, in the order the script issued them. In a parallel multi-lane
script every lane issues its first call at start, so changing one early prompt
re-runs every later call, finished ones included, even when their own prompt is
byte-identical.
This happened on 2026-09-23. Three stop-edit-resume cycles, each done to inject one new user request, killed agents that had been working for 20 to 77 minutes. The operator believed they had run "a few minutes", having counted conversation turns instead of reading timestamps. Each resume also re-ran implementation steps that had already finished.
Default: never stop a run to inject a change
When the user adds or amends a requirement while a workflow runs:
- Acknowledge it and record it in the plan or task list.
- Route it without touching the run:
- An independent task becomes a separate workflow on its own branch and worktree. Launch it now if it cannot conflict with the running lanes, otherwise after the run.
- A correction to a task that has not started yet, or that is in progress, becomes a follow-up task that runs after the lane finishes. It amends the result, and the integrator reconciles it.
- Tell the user where the change will land and when.
The only reasons to stop
Stop only when the run is doing damage: destroying data, pushing, spending on work the user cancelled, or building something the user reversed that is expensive to undo. Even then:
- Measure, never estimate. For every agent in flight, read the first and last
timestamps of its transcript (
agent-<id>.jsonlin the workflow transcript directory) and compare them with the current UTC time. Conversation turns are not a clock: the user may have been away for an hour between two messages. - List the finished calls that the stop will make run again.
- Give the user the concrete cost (agents × minutes of context lost, steps that will re-run) and wait for an explicit go.
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.
- 15d ago First seen · 72 lines · 42 tokens per session scan A 32e8ccaacffa
workflow-change-control is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 807 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 2026-10-14.
Other skills, from other repositories
pipefy-process-intelligence
Use this skill when the user wants to analyze an existing pipe for improvement opportunities — automation gaps, manual bottlenecks, missing AI agents, field conditions, or adjacent processes. Acts as a process analyst: investigates, diagnoses, and improves the pipe in progressive rounds — each round delivers visible…
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.