manage

Name: manage
Author: Borda

23stars3forks

How to install manage?

borda/ai-rig/manage

$npx -y skills add Borda/AI-Rig --skill manage

Installs into the current project.

Summary

Create, update, or delete agents, skills, rules, and hooks with full cross-reference propagation. Trivial edits (typos, small fixes ≤10 words) applied inline without agent; .md content-edits delegated to foundry:curator; code file edits (.js, .py, .ts) delegated to foundr

Files · 1

View on GitHub

SKILL.md

1	> Note: `disable-model-invocation: true` — `/manage` user-invoked only, no `Skill()` chaining from orchestrators. When suggesting `/manage` as follow-up, invoking skill must present as user-run command, not auto step.
2
3	<objective>
4
5	Manage lifecycle of agents, skills, rules, hooks in `.claude/`. Handles creation with rich domain content, atomic renames with cross-ref propagation, content editing (trivial edits inline; `.md` files → foundry:curator; code files `.js`/`.py`/`*.ts` → foundry:sw-engineer; rule edits inline), clean deletion with broken-ref cleanup. Keeps MEMORY.md inventory in sync with disk.
6
7	</objective>
8
9	<inputs>
10
11	- $ARGUMENTS: required, one of:
12	- `create agent <name> "description"` — create new agent with generated domain content
13	- `create skill <name> "description"` — create new skill with workflow scaffold
14	- `create rule <name> "description"` — create new rule file with frontmatter and sections
15	- `update <name> <new-name>` — rename; type auto-detected from disk
16	- `update <name> "change description"` — content-edit; trivial → inline, `.md` → foundry:curator, code → foundry:sw-engineer, rule → inline
17	- `update <name> <spec-file.md>` — content-edit from spec file; trivial → inline, `.md` → foundry:curator, code → foundry:sw-engineer, rule → inline
18	- `delete <name>` — delete; type auto-detected from disk (agents, skills, rules, hooks); asks user if ambiguous
19	- `add perm <rule> "description" "use case"` — add permission to settings.json allow list and permissions-guide.md
20	- `remove perm <rule>` — remove permission from settings.json allow list and permissions-guide.md
21
22	- Names must be kebab-case (lowercase, hyphens only)
23	- Descriptions must be quoted when containing spaces
24	- Permission rules use Claude Code format: `WebSearch`, `Bash(cmd:*)`, `WebFetch(domain:example.com)`
25	- `--skip-audit` — optional flag: skip Step 9 `/audit` validation (use inside `audit fix` loop to avoid recursion)
26	- Spec-file paths must be quoted — `update <name> <spec-file.md>` requires the spec path quoted if it contains any whitespace (e.g. `update my-agent "docs/My Spec.md"`); unquoted paths with spaces split into multiple arguments and trigger argument-shape mismatch. Recommended: keep spec filenames free of spaces.
27
28	Update/delete mode — name looked up across agents, skills, rules automatically:
29
30	- One match on disk → proceed with that type
31	- Multiple matches → `AskUserQuestion`: (a) agent, (b) skill, (c) rule
32	- No match → report error and stop
33
34	Update second-argument discrimination:
35
36	- Two bare kebab-case args (second arg no spaces, no `.md` extension) → rename mode
37	- One name + quoted string → content-edit mode (trivial → inline; `.md`: foundry:curator; code `.js`/`.py`/`*.ts`: foundry:sw-engineer; rule: inline)
38	- One name + path ending in `.md` → content-edit mode (trivial → inline; `.md`: foundry:curator; code `.js`/`.py`/`*.ts`: foundry:sw-engineer; rule: inline)
39
40	Examples:
41
42	- `/foundry:manage create agent task-planner "Planning specialist for decomposing epics into actionable tasks"`
43	- `/foundry:manage update my-agent "add a section on error handling patterns"`
44	- `/foundry:manage update optimize docs/specs/YYYY-MM-DD-<spec-name>.md`
45	- `/foundry:manage delete old-agent-name`
46	- `/foundry:manage add perm "Bash(jq:*)" "Parse and filter JSON" "Extract fields from REST API responses"`
47
48	</inputs>
49
50	<constants>
51
52	- AGENTS_DIR: `.claude/agents`
53	- SKILLS_DIR: `.claude/skills`
54	- RULES_DIR: `.claude/rules`
55	- HOOKS_DIR: `.claude/hooks`
56	- AVAILABLE_COLORS: indigo, lime, magenta, teal, violet
57
58	Each Step 4 spawn applies the health monitoring in `_shared/agent-spawn-protocol.md` §8b — rely on the harness completion notification, then read the agent's output file; optional single `health_sentinel.py` probe per turn (no sleep loop). Substitute only its own `<ID>` suffix and output-file glob; do not

People who liked this also viewed

6 picks

Type

manage

23stars3forks

View on GitHub

How to install manage?

borda/ai-rig/manage

$npx -y skills add Borda/AI-Rig --skill manage

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	> Note: `disable-model-invocation: true` — `/manage` user-invoked only, no `Skill()` chaining from orchestrators. When suggesting `/manage` as follow-up, invoking skill must present as user-run command, not auto step.
2
3	<objective>
4
5	Manage lifecycle of agents, skills, rules, hooks in `.claude/`. Handles creation with rich domain content, atomic renames with cross-ref propagation, content editing (trivial edits inline; `.md` files → foundry:curator; code files `.js`/`.py`/`*.ts` → foundry:sw-engineer; rule edits inline), clean deletion with broken-ref cleanup. Keeps MEMORY.md inventory in sync with disk.
6
7	</objective>
8
9	<inputs>
10
11	- $ARGUMENTS: required, one of:
12	- `create agent <name> "description"` — create new agent with generated domain content
13	- `create skill <name> "description"` — create new skill with workflow scaffold
14	- `create rule <name> "description"` — create new rule file with frontmatter and sections
15	- `update <name> <new-name>` — rename; type auto-detected from disk
16	- `update <name> "change description"` — content-edit; trivial → inline, `.md` → foundry:curator, code → foundry:sw-engineer, rule → inline
17	- `update <name> <spec-file.md>` — content-edit from spec file; trivial → inline, `.md` → foundry:curator, code → foundry:sw-engineer, rule → inline
18	- `delete <name>` — delete; type auto-detected from disk (agents, skills, rules, hooks); asks user if ambiguous
19	- `add perm <rule> "description" "use case"` — add permission to settings.json allow list and permissions-guide.md
20	- `remove perm <rule>` — remove permission from settings.json allow list and permissions-guide.md
21
22	- Names must be kebab-case (lowercase, hyphens only)
23	- Descriptions must be quoted when containing spaces
24	- Permission rules use Claude Code format: `WebSearch`, `Bash(cmd:*)`, `WebFetch(domain:example.com)`
25	- `--skip-audit` — optional flag: skip Step 9 `/audit` validation (use inside `audit fix` loop to avoid recursion)
26	- Spec-file paths must be quoted — `update <name> <spec-file.md>` requires the spec path quoted if it contains any whitespace (e.g. `update my-agent "docs/My Spec.md"`); unquoted paths with spaces split into multiple arguments and trigger argument-shape mismatch. Recommended: keep spec filenames free of spaces.
27
28	Update/delete mode — name looked up across agents, skills, rules automatically:
29
30	- One match on disk → proceed with that type
31	- Multiple matches → `AskUserQuestion`: (a) agent, (b) skill, (c) rule
32	- No match → report error and stop
33
34	Update second-argument discrimination:
35
36	- Two bare kebab-case args (second arg no spaces, no `.md` extension) → rename mode
37	- One name + quoted string → content-edit mode (trivial → inline; `.md`: foundry:curator; code `.js`/`.py`/`*.ts`: foundry:sw-engineer; rule: inline)
38	- One name + path ending in `.md` → content-edit mode (trivial → inline; `.md`: foundry:curator; code `.js`/`.py`/`*.ts`: foundry:sw-engineer; rule: inline)
39
40	Examples:
41
42	- `/foundry:manage create agent task-planner "Planning specialist for decomposing epics into actionable tasks"`
43	- `/foundry:manage update my-agent "add a section on error handling patterns"`
44	- `/foundry:manage update optimize docs/specs/YYYY-MM-DD-<spec-name>.md`
45	- `/foundry:manage delete old-agent-name`
46	- `/foundry:manage add perm "Bash(jq:*)" "Parse and filter JSON" "Extract fields from REST API responses"`
47
48	</inputs>
49
50	<constants>
51
52	- AGENTS_DIR: `.claude/agents`
53	- SKILLS_DIR: `.claude/skills`
54	- RULES_DIR: `.claude/rules`
55	- HOOKS_DIR: `.claude/hooks`
56	- AVAILABLE_COLORS: indigo, lime, magenta, teal, violet
57
58	Each Step 4 spawn applies the health monitoring in `_shared/agent-spawn-protocol.md` §8b — rely on the harness completion notification, then read the agent's output file; optional single `health_sentinel.py` probe per turn (no sleep loop). Substitute only its own `<ID>` suffix and output-file glob; do not

People who liked this also viewed

6 picks

Type