- Add feynman as third target (~/.feynman/agent/agents) alongside opencode
and claude. Default targets now: opencode,claude,feynman. Each target
gets its own parked source dir (formats differ: opencode permission/mode,
claude PascalCase tools, feynman lowercase tools + thinking/output).
- Fix fzf {} preview shell-escape bug: {} in fzf is shell-escaped, so
"$PARKED/{}.md" embedded literal quotes into the path and broke preview.
Switched to "$PARKED"/{}.md across all 8 preview lines.
- pick: union-of-parked across all 3 targets for category list (so a
feynman-only agent like researcher is reachable). After agent multi-select
(rows annotated [oc,cl,fy] showing parked-in targets), prompt target
picker (all / opencode / claude / feynman, TAB for multi).
- disable-pick: rewritten to show union of actives across all 3 targets
with [oc,cl,fy] indicators, then target picker for which to disable from.
- cmd_status: 3-target counts (parked + active) with all-3 intersection.
- reindex: tracks parked.{opencode,claude,feynman} + active list across 3.
- New env vars: OPC_AGENTS_FEYNMAN_PARKED, OPC_AGENTS_FEYNMAN_ACTIVE.
opc-agents
Multi-target agent manager for opencode + Claude Code + Feynman. Per-target parked sources (different formats), shared CLI surface. Companion to opc-skills.
Why
opencode injects every agent's frontmatter into the calling agent's tool registry. With 100+ agents the registry alone burns ~280K tokens of context before the user types a prompt. Park the ones you don't need this week.
opencode, Claude Code, and Feynman use three different agent frontmatter formats:
| target | tools field | extra fields |
|---|---|---|
| opencode | permission: { edit, bash, webfetch, … } |
mode: (primary/subagent), temperature: |
| claude | tools: Read, Glob, Grep, … (PascalCase) |
color: |
| feynman | tools: read, write, grep, … (lowercase) |
thinking:, output:, defaultProgress:, inheritProjectContext: |
opc-agents keeps a separate parked source per target and copies the appropriate format for each --target selection. The upstream personas/build.py pipeline can produce all three formats from one persona definition, so a --target all enable can deliver the same persona to all three platforms in their native format.
Install
ln -s ~/Documents/opc-agents/bin/opc-agents ~/.local/bin/opc-agents
Ensure ~/.local/bin is on your PATH.
Layout it expects
~/Documents/personas/agents-opencode-archive/ # parked, opencode format
<name>.md (frontmatter: mode, permission, …)
INDEX.json + INDEX.md (canonical index — also tracks claude+feynman parked/active)
~/Documents/personas/agents-claude-archive/ # parked, claude format
<name>.md (frontmatter: tools: Read, Glob, …)
~/Documents/personas/agents-feynman-archive/ # parked, feynman format
<name>.md (frontmatter: tools: read,write,… thinking, output, defaultProgress)
~/.config/opencode/agents/ # active, opencode target
~/.claude/agents/ # active, claude target
~/.feynman/agent/agents/ # active, feynman target
(~/Documents/opencode-agents-parked is symlinked to personas/agents-opencode-archive for backward compat.)
Override via env:
OPC_AGENTS_PARKED— opencode parked source (defaultpersonas/agents-opencode-archive)OPC_AGENTS_CLAUDE_PARKED— claude parked source (defaultpersonas/agents-claude-archive)OPC_AGENTS_FEYNMAN_PARKED— feynman parked source (defaultpersonas/agents-feynman-archive)OPC_AGENTS_ACTIVE— opencode active dir (default~/.config/opencode/agents)OPC_AGENTS_CLAUDE_ACTIVE— claude active dir (default~/.claude/agents)OPC_AGENTS_FEYNMAN_ACTIVE— feynman active dir (default~/.feynman/agent/agents)OPC_AGENTS_TARGETS— comma-separated default targets (defaultopencode,claude,feynman)
Targets
enable, disable, and disable-all accept --target / -t (opencode, claude, feynman, all, or comma-separated subset). Default is opencode,claude,feynman. both is preserved as a legacy alias for opencode,claude (no feynman).
An agent missing in a target's parked source is skipped with a clear message — there is no automatic format conversion at the opc-agents layer. Cross-format conversion happens upstream in personas/build.py.
Commands
Inspection
status |
counts of active vs parked across all 3 targets + opencode primary/subagent breakdown |
list {active|parked|all} |
list agent names |
categories / cats |
prefix-based base-persona counts (PARKED) |
variants / vars |
suffix-based variant counts (PARKED) — eg. salva, iran |
Single-agent operations
enable [--target T] <name> |
enable single agent (copy parked → active) in selected targets |
disable [--target T] <name> |
disable single agent (remove from active; keep parked) |
disable-all [--target T] [-y|--yes] [--keep-primary] |
disable every active agent (asks for confirmation) |
Bulk by axis
enable-category <prefix> / disable-category <prefix> |
fzf multi-pick by base persona prefix (eg. frodo, marshal) |
enable-variant <suffix> / disable-variant <suffix> |
bulk by variant suffix (eg. salva, iran, russian-doctrine) |
enable-domain <domain> / disable-domain <domain> |
bulk by Domain: value in description (live scan) |
Interactive / search
pick |
fzf: union-parked category → multi-select agents → target picker → enable |
disable-pick |
fzf: union-of-actives → category → multi-select → target picker → disable |
search [query] / disable-search |
fzf fuzzy search across name + mode + domain + variant + description |
reindex |
rebuild INDEX.json / INDEX.md (extracts persona/variant/domain from frontmatter; tracks all 3 targets) |
fzf is required for the interactive pickers; jq for the search variants; python3 for reindex.
pick flow
- Choose a category from the union of parked agents across all 3 targets (so a feynman-only agent like
researcheris reachable viapick) - Multi-select agents — each row shows
[parked-in:oc,cl,fy]indicators - Target picker appears:
all/opencode/claude/feynman—TABfor multi-select;ENTERon highlightedall(default) sends to all three - cmd_enable copies the appropriate parked file per target; targets without that agent in their parked dir are skipped with
[t] not parkedmessage
disable-pick flow
Lists the union of all active agents across the three targets, with each entry annotated [oc,cl,fy] showing where it's currently active. After multi-select, the target picker decides which target(s) to remove from.
Notes
- Each agent is a single
<name>.mdfile with YAML frontmatter; format depends on target (see table above). disable*commands never delete data — they remove the active copy and keep (or restore) the parked copy. Re-enable withopc-agents enable <name>.--keep-primaryondisable-allskips agents withmode: primary(opencode-format only — claude and feynman don't have amode:field).- Common agent prefixes seen in personas:
frodo-,marshal-,sentinel-,bastion-,neo-,oracle-,warden-,polyglot-, etc.
Implementation notes
fzfplaceholder{}is shell-escaped automatically — preview commands use"$PARKED"/{}.md(variable quoted,{}unquoted) so bash concatenation produces a clean path.
Differences from opc-skills
opc-skills |
opc-agents |
|
|---|---|---|
| Unit | directory containing SKILL.md |
single <name>.md file |
| Frontmatter fields used | name, description, domain, subdomain, tags |
description, mode, tools, permission |
| Format per target | identical (folder + SKILL.md) | different per target (oc / claude / feynman) |
| Parked source-of-truth | one (skills-archive) |
three (one per target format) |
| Shared refs sync | yes (_platform-mapping.md) |
n/a |
disable-all flags |
-y |
-y, --keep-primary |
| Status breakdown | active/parked | + opencode primary/subagent counts |