mirror of https://github.com/magnus919/agent-skills.git synced 2026-09-11 19:47:12 +03:00

Files

T

Magnus HedemarkandGitHub e10508b034 feat(bmad): add BMad control-plane protocol skill (#400 )

* feat(bmad): add BMad control-plane protocol skill

New standalone methodology skill that lets any agent run the BMad method
(Breakthrough Method of Agile AI-Driven Development) as a harness-agnostic
control-plane protocol: five-field intent contracts, direct/bounded/initiative
classification, review-as-triage, failure routing by layer, and autonomy gating
with machine-readable spec status.

- SKILL.md protocol core with progressive disclosure + When not to use
- README.md human-facing install guide
- 9 references: protocol, classification, spec, lifecycle, project-context,
  review-and-failure-routing, autonomy, party-mode, adoption
- 4 templates: SPEC, INTENT, STORY, REVIEW
- scripts/check-spec.py + 16 tests (stdlib, deterministic spec validation)
- evals/evals.json: 9 output-quality cases
- Routing seams from bmad to adjacent skills and back from
  spec-driven-development, product-shaping, implementation-planning, neckbeard
- Catalog updates: root README, skill-triggers, marketplace/plugin/llms.txt

Closes #399

* fix(bmad): address droid-review findings

- check-spec.py: skip headings inside fenced/indented code blocks so a spec
  cannot PASS on section text that only appears in a code sample
- check-spec.py: catch UnicodeDecodeError on non-UTF-8 files and report FAIL
  instead of crashing
- STORY.md template: add created key for resumability/traceability parity
- SPEC.md template: split in-progress and in-review status bullets
- add 2 regression tests (heading-in-fence, non-UTF-8)

* fix(bmad): address droid-review round 2

- check-spec.py: read specs with utf-8-sig so a UTF-8 BOM cannot silently
  disable the frontmatter status check
- check-spec.py: handle standard YAML inline comments after status values
  (status: draft  # pending review) without a false FAIL
- references/protocol.md: make lifecycle phrasing consistent with
  lifecycle.md — four phases plus a learning closeout
- add 2 regression tests (BOM, inline comment)

* fix(bmad): tolerate trailing whitespace on frontmatter delimiters

A spec whose --- delimiter lines carry trailing spaces or tabs would silently
disable the status check and let an invalid status PASS. Relax the delimiter
pattern and add a regression test.

* fix(bmad): ignore inline comments in quoted status values

* fix(bmad): tolerate leading blank lines before frontmatter

* fix(bmad): fail closed on unparseable frontmatter, matching fence markers

Address droid-review round 5 and 6 findings as a single closed class:
- Fail closed when a file opens with a --- delimiter that cannot be parsed,
  so no whitespace/frontmatter permutation can silently disable the status
  check (previously: unparseable frontmatter was treated as 'no status'
  warning, letting an invalid status PASS).
- Track fence opener markers in collect_headings so a mismatched fence no
  longer closes a code block early (false-PASS on missing sections) and an
  unclosed fence no longer swallows real headings.
- Accept empty well-formed frontmatter (---\n---) and closing delimiters
  without a trailing newline.
- STORY.md template: parent-spec points at the sibling SPEC.md.
- README: status vocabulary is not a strict linear chain; blocked is a
  resumable routing signal.

Whitespace/frontmatter mutation sweep: 9 formatting variants x valid/invalid
status all verdict correctly; malformed delimiters fail closed. 29 tests.

2026-08-24 08:05:43 -04:00

2.3 KiB

Raw Permalink Blame History

Party Mode: Multi-Persona Deliberation

Party Mode puts several BMad roles into one conversation to find missing concerns, pressure-test a plan, run a post-mortem, or debate a trade-off. It is a deliberation protocol — not an implementation method.

When to use

Trade-off decisions with several defensible answers.
Finding missing concerns before committing to a plan.
Pressure-testing a plan or spec.
Post-mortems.
Design debates.

Execution modes

Mode	Mechanics	Cost	Independence
session	One model voices all personas inline	Cheapest, most fluid	None — one shared mind
auto	Inline unless separate agents would change the answer	Depends	Conditional
subagent	Separate agent for each persona in substantive rounds	Higher	Real separation of reasoning paths
agent-team	Persistent multi-agent team in supported harnesses	Highest	Real, persistent

The mode is not cosmetic. Session mode is cheap and fluid but cannot provide genuinely independent reasoning — the perspectives share one underlying mind. Subagent and team modes cost more but reduce shared-context convergence, which is the whole point when independence matters.

The independence caveat

Role names provide continuity, expectations, and a consistent point of view. They do not guarantee separate cognition. Five names in a conversation do not create five minds. Role separation is still valuable with one model — it changes the checklist, priorities, and questions the model is instructed to apply — but never describe it as independent review unless the reasoning paths are actually independent.

Ground rules

Each persona applies its own checklist and asks its own questions; do not let one persona's conclusion pre-empt another's.
Surface disagreements explicitly; consensus among personas is not independent validation.
Converge toward a decision landscape: shared risks, remaining disagreements, confidence, and a recommended path — not a false unanimity.
End with the decision or the open question that needs the human.

Harness mapping

In this repository, agent-council is the nearest equivalent for genuinely separate deliberation agents, and agent-evals-and-observability covers independent evaluators. Use them when the independence of the reasoning paths matters to the decision.

2.3 KiB Raw Permalink Blame History