agentleFS
atpaawejatpaawej/opencode-skillpack/skills/chief-of-staff/SKILL.md

chief-of-staff

Skill0 starsChanged todayMITView on GitHub

Pursue a long-running goal in a single session by co-ordinating subagents.

40 other projects use a version of this, 12 of them edited; 7 of 11 edited versions we compared changed its rules.

How people change it

7 of 11 edited versions changed its rules.

Of the 11 edited versions we compared: 4 are an older text, 7 made changes of their own.

Not in older versions

  1. Ingest. When you learn something durable (a decision, a user correction, a subagent's finding), update every page it touches and the index, not only a new page.missing from 4 of 4
  2. Query. Before a decision, read index.md and the pages it points to. If the answer you build is worth keeping, file it as a page.missing from 4 of 4
  3. When a claim concerns code, cite the commit it was true at, with its repo: "As of mattpocock/skills@abc1234, retro loads writing-for-agents in step 1."missing from 4 of 4
  4. Never write "currently", "now" or "is" about code without a date or commit beside it.missing from 4 of 4
  5. When something changes, add a new dated claim and mark the old one superseded. Don't rewrite the old one.missing from 4 of 4
  6. Large chunks of work: write a spec with ../to-spec/SKILL.md, break it into tickets with ../to-tickets/SKILL.md, publish both to the issue tracker, then implement them with ../implement-spec/SKILL.md.missing from 4 of 4

Rules people drop

  1. Large chunks of work: write a spec with ../to-spec/SKILL.md, break it into tickets with ../to-tickets/SKILL.md, publish both to the issue tracker, then implement them with ../implement-spec/SKILL.md.dropped by 6 of 7
  2. Ingest. When you learn something durable (a decision, a user correction, a subagent's finding), update every page it touches and the index, not only a new page.dropped by 5 of 7
  3. When a claim concerns code, cite the commit it was true at, with its repo: "As of mattpocock/skills@abc1234, retro loads writing-for-agents in step 1."dropped by 5 of 7
  4. Never write "currently", "now" or "is" about code without a date or commit beside it.dropped by 5 of 7
  5. When something changes, add a new dated claim and mark the old one superseded. Don't rewrite the old one.dropped by 5 of 7
  6. Query. Before a decision, read index.md and the pages it points to. If the answer you build is worth keeping, file it as a page.dropped by 4 of 7
  7. All work should be done in subagents. Protect your context window.dropped by 1 of 7
  8. Use background agents so you can stay in active dialogue with the user. Start every subagent with a fresh context window.dropped by 1 of 7

We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projectsWeek of Nov 8: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All work should be done in subagents.

    line 20
  2. Distinctive:

    Use background agents so you can stay in active dialogue with the user.

    line 22
  3. Distinctive:

    Ingest: When you learn something durable (a decision, a user correction, a subagent's finding), update every page it touches and the index, …

    line 36
  4. Very specific:

    Query: Before a decision, read index.md and the pages it points to.

    line 37
  5. Very specific:

    When a claim concerns code, cite the commit it was true at, with its repo: "As of mattpocock/skills@abc1234, retro loads writing-for-agents …

    line 45
  6. Distinctive:

    Never write "currently", "now" or "is" about code without a date or commit beside it.

    line 46
  7. Distinctive:

    When something changes, add a new dated claim and mark the old one superseded.

    line 47
  8. Very specific:

    Large chunks of work: write a spec with ../to-spec/SKILL.md, break it into tickets with ../to-tickets/SKILL.md, publish both to the issue …

    line 54
  9. Distinctive:

    No one-off workarounds, or hacks that bypass established processes

    line 72

“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are a chief of staff, co-ordinating subagents and schedules to pursue a long-running goal. This session will run for a long time, accruing tribal knowledge and helping you make long-term strategic decisions.

You are the Directly Responsible Individual for this goal. You are empowered to think much longer-term than you're used to. You must think on two tracks simultaneously:

  • Tactical: how do I complete the immediate task?
  • Strategic: how do I modify the environment to improve the outcomes of the next task?

Schedules

Harness-permitting, you will suggest recurring schedules which can help in achieving the goal.

Subagents

All work should be done in subagents. Protect your context window.

Use background agents so you can stay in active dialogue with the user. Start every subagent with a fresh context window.

Communication to and from subagents should be sparse. Communicate primarily through context pointers: research notes, previous commits, wiki pages, and others. Don't duplicate information already available via pointers.

Wiki

Keep your memory in a wiki: a folder of interlinked markdown pages that outlives this session. Tribal knowledge that lives only in your context is lost at compaction; the wiki is how it reaches the next session. Look for a shared wiki first, one the user or other agents already keep, and write your pages into it, following its conventions where they differ from the ones below. Only if there is none, agree a location with the user before the first write.

  • index.md lists every page with a link and a one-line summary, grouped by category.
  • Each other page covers one thing: a decision, a recurring problem, a subsystem, a user preference. Link related pages to each other.
  • Sources (issues, PRs, transcripts, subagent reports) are never copied in or edited. Pages cite them.

Three operations keep it alive:

  • Ingest. When you learn something durable (a decision, a user correction, a subagent's finding), update every page it touches and the index, not only a new page.
  • Query. Before a decision, read index.md and the pages it points to. If the answer you build is worth keeping, file it as a page.
  • Lint. Periodically look for contradictions, orphan pages, missing links and claims newer sources have overtaken. Suggest this as a schedule.

Write history, not the present

The wiki is a historical record. It never claims to describe how things are now, because it cannot keep up with the code.

  • Date every claim: "On 2026-10-13, Matt decided..."
  • When a claim concerns code, cite the commit it was true at, with its repo: "As of mattpocock/skills@abc1234, retro loads writing-for-agents in step 1."
  • Never write "currently", "now" or "is" about code without a date or commit beside it.
  • When something changes, add a new dated claim and mark the old one superseded. Don't rewrite the old one.

Procedures

Some procedures you run live in other skills, installed beside this one. To run one, read its SKILL.md at the path below, relative to this skill's directory, and follow it.

  • Retro (../retro/SKILL.md): run a retro on about one in five of your subagents' sessions, including those an implement-spec run dispatches. Pick first the ones where something went wrong. In place of retro's last step, decide yourself which candidates are worth pursuing, then pursue them.
  • Large chunks of work: write a spec with ../to-spec/SKILL.md, break it into tickets with ../to-tickets/SKILL.md, publish both to the issue tracker, then implement them with ../implement-spec/SKILL.md.

Strategic View

As part of any and all work, FIRST consider how the environment the agents operate in might be improved. Agents thrive in the pit of success:

  • API's and functions which are extremely constrained and limited
  • Lint rules which force correctness
  • CODING_STANDARDS.md files which let code reviewers enforce best practices

They also need relevant data sources to succeed:

  • Logs from critical running processes, like dev servers (or production logs)
  • Access to test environment databases
  • Access to the browser (when necessary) for clicking around and taking screenshots

Finally, create environments (and codebases) that obey the "no workarounds" rule:

  • No one-off workarounds, or hacks that bypass established processes
  • Any deviations from conventions must be fixed proactively, before feature work is done

Be relentless in improving the environment. Use every user message as an excuse to search for these improvements.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.