Install
$ agentstack add skill-evolvehq-docflow-new-plan ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
new-plan
Add one item to the implementation queue.
Step 0 — Preconditions and context
- Confirm the repo is bootstrapped and a
plan/queue exists. If the
repo was bootstrapped without a plan folder (Q4a = skip), stop and say so — there is no queue to add to.
- Read
CONVENTIONS.mdfor the plan-folder convention and the
completion event, and plan/README.md if present. Resolve plan/ against the artefact root recorded there (default: repository root).
ls plan/todo/to learn existing numbers and priority ordering.
Step 0.5 — Assessment (run first)
Run the shared assessment protocol before queueing:
- Opt-out gate first. Ask whether to run the assessment or skip to
writing the item. Recommend running it when the request arrived with little or no context; recommend skipping when the item is already fully specified.
- Ask the questions below one at a time, each with a **recommended
option** and a one-line reason; wait for each answer.
- Use structured selection (single- or multiple-choice). If the host
exposes a structured single-/multi-select question tool, use it and mark the recommended option; otherwise list options A/B/C in plain text and name the recommended one. Use free text only where an enumerable set is impossible (e.g. the scope summary).
- The operator decides. Never proceed past a question without an
answer, and never guess scope when invoked with no context.
Questions (skip any the request already answers):
- Owning ADR(s) — select from the catalogue (single or multiple).
Recommended: the ADR named in the request.
- Dependencies — none, or select the plan items / ADRs that must
land first. Recommended: none.
- Priority / position — next number, or insert ahead of existing
items. Recommended: next number.
- Scope & exit criteria — free text, mapped to the owning ADR's
numbered acceptance criteria where possible.
Step 1 — Identify the owning ADR(s)
- Ask which ADR(s) this work implements. Validate they exist in
adr/.
- Normally a queue item tracks an Accepted ADR. If the named ADR is
still Proposed, warn — you can queue ahead of acceptance, but the work is not yet authorised. If it has no ADR at all, suggest running the new-adr skill first; plan items should trace to a decision.
- In a federation (a
federation.mdexists): the owning ADR may live
in another repo (the home/central). Name it by its federation identity (/NNNN-slug); the plan item itself lives in this repo — the one whose code the work changes. A decision spanning several repos gets one item per affected repo, each tracing to the same owning ADR (the grouping point — no umbrella record).
Step 2 — Pick number and position
plan/todo/NNNN-.md, zero-padded. Lower numbers run first —
ask where this sits in priority and renumber neighbours only if the user wants it inserted ahead of existing items.
Step 3 — Write the item
The file names, at minimum:
- Owning ADR(s) by relative path.
- Scope — what is in, what is explicitly out.
- Exit criteria — map directly to the ADR's numbered acceptance
criteria where possible.
- Dependencies — other plan items or ADRs that must land first.
Step 4 — Commit
Conventional Commit. If the file references an ADR by number in its body that is fine (the plan queue is internal — the ADR-privacy rule only forbids ADR references in user-visible product surfaces).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: EvolveHQ
- Source: EvolveHQ/docflow
- License: MIT
- Homepage: https://evolvehq.github.io/docflow/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.