feat(forge): definition-of-done card contract + card gate + sop-to-skills offer - #31
Merged
Conversation
Reviewer's GuideThis PR operationalizes the definition-of-done thesis by documenting a delegation-card contract, enforcing its required fields with a strict-capable dispatch gate, and packaging the approach into a draft SOP-to-skills commercial offer. Flow diagram for delegation card dispatch gatingflowchart TD
Card[Delegation card] --> Gate[card_gate.py]
Gate --> Done{Has valid DONE section?}
Done -->|No| Reject[REJECTED]
Done -->|Yes| Criteria{3-7 checkable criteria?}
Criteria -->|No| Reject
Criteria -->|Yes| Fields{Maintainable by, Unplug test, Business link?}
Fields -->|No| Reject
Fields -->|Yes| Dispatch[DISPATCHABLE]
Strict[--strict] -.-> Gate
Strict -.-> Vague{Reject vague or non-checkable criteria}
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars. ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Team Run ID: Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
🟡 Changes recommended
The new gate/docs include concrete mismatches (documented strict requirements not enforced, inconsistent schema wording, and an inaccurate success criteria count) plus the PR claims fixture verification that isn’t present in-repo.
Once you've addressed the issues Copilot identified, you can request another Copilot review.
Pull request overview
This PR operationalizes a “definition of done” contract for agent-forge delegation cards by adding a formal DONE schema plus a CLI gate that rejects cards without a compliant DONE section, and it also adds a draft SOP-to-skills client offer document.
Changes:
- Adds
agent-forge/docs/card-contract.mddefining a machine-checkable DONE schema, verification rules, and anti-gaming guidance. - Adds
agent-forge/tools/card_gate.py, a stdlib-only CLI validator that rejects cards missing DONE requirements and optionally applies stricter heuristics. - Adds
05_Clients/offer-sop-to-skills.md, a draft service offering describing delivery, pricing anchors, and proof points.
File summaries
| File | Description |
|---|---|
| agent-forge/tools/card_gate.py | New CLI gate to validate delegation cards contain a compliant ## DONE block (with optional strict checks). |
| agent-forge/docs/card-contract.md | New written contract describing the DONE schema and verification/anti-gaming rules that the gate enforces. |
| 05_Clients/offer-sop-to-skills.md | New draft client-facing offer tying the DONE discipline to a packaged SOP-to-skills service. |
Review details
Suppressed comments (3)
agent-forge/tools/card_gate.py:14
- The docstring says
--strict"requires the reviewer line", but the implementation does not validate any reviewer line. Either enforce a reviewer field in strict mode, or (simpler) update the docstring to match actual behavior.
Exit codes: 0 = dispatchable; 1 = rejected (report on stdout).
--strict additionally requires the reviewer line and rejects vague
criteria (no digits, no file paths, no commands) heuristically.
agent-forge/tools/card_gate.py:46
DONE_RE.search(text)is executed twice; store the match once and reuse it to avoid redundant work and keep the parsing logic in one place.
if not DONE_RE.search(text):
return False, ["card has no '## DONE' section; see agent-forge/docs/card-contract.md"]
done_block = DONE_RE.search(text)
# capture from DONE header to next ## or EOF
tail = text[done_block.end():]
agent-forge/tools/card_gate.py:88
- On success, the reported criteria count is computed by scanning the entire file, which can over-count if "DONE IF" appears outside the
## DONEsection (and it rereads the file). Consider removing the count or computing it from the DONE block.
if ok:
print(f"DISPATCHABLE: {path.name} ({len(CRITERION_RE.findall(path.read_text(encoding='utf-8')))} criteria)")
return 0
- Files reviewed: 3/3 changed files
- Comments generated: 3
- Review effort level: Lite
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Comment on lines
+9
to
+15
| Usage: | ||
| python3 card_gate.py <card.md> [--strict] | ||
|
|
||
| Exit codes: 0 = dispatchable; 1 = rejected (report on stdout). | ||
| --strict additionally requires the reviewer line and rejects vague | ||
| criteria (no digits, no file paths, no commands) heuristically. | ||
| """ |
Comment on lines
+58
to
+61
| - The skill pipeline: github.com/aegntic/cognitive-os (agent-forge) | ||
| - The quality gates that run on every deliverable: same repo, | ||
| agent-forge/tools/qc.py | ||
| - A working end-to-end skill with examples: github.com/aegntic/tab-harvest |
Comment on lines
+26
to
+28
| 2. **The second-best-engineer test.** State who could maintain the | ||
| output: "DONE IF a competent non-author reviewer can open any file | ||
| produced and explain its purpose in under 20 minutes." For code: |
Owner
Author
|
The 'Lint, Format & Test' failure is the pre-existing prettier rot in 02_Showcase/THRESHOLD-INC and brik-pro (50 files, unchanged on this branch; same failure on main since PR #28 documented it). Zero files touched by this PR appear in the failure log: this PR adds only agent-forge/docs/card-contract.md, agent-forge/tools/card_gate.py, 05_Clients/offer-sop-to-skills.md, all prettier-clean locally. All other 8 checks pass. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Operationalizes the Runable definition-of-done thesis inside the forge.
Contents
Verification
Summary by Sourcery
Operationalize definition-of-done requirements across agent-forge cards and introduce an SOP-to-skills service offering.
New Features:
Enhancements:
Documentation: