Borrowing it
Nothing to install: this file belongs to asta-nguyen/kamehadb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/asta-nguyen/kamehadb/main/.agents/skills/plan-feature/SKILL.mdgit clone --depth 1 https://github.com/asta-nguyen/kamehadbWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/asta-nguyen/kamehadb/plan-feature)<a href="https://agentmods.dev/skills/asta-nguyen/kamehadb/plan-feature"><img src="https://agentmods.dev/badge/skills/asta-nguyen/kamehadb/plan-feature/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asta-nguyen/kamehadb/plan-feature"><img src="https://agentmods.dev/badge/skills/asta-nguyen/kamehadb/plan-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.01882 |
| Opus 5.5 | $0.00017 | $0.00753 |
| Sonnet 5.5 | $0.00009 | $0.00376 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
plan-feature scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 19d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Feature
Turn a design into a short execution plan before editing code. For a new change,
brainstorm-feature writes design.md and calls this skill before any approval;
the user then approves design.md and tasks.md together, once. "The design"
means that written design.md. Save tasks.md beside it in the change folder
(using-devkit's ## Change lifecycle). A legacy design with no change folder is
covered by ../using-devkit/references/legacy.md; read it when you meet one.
Create the folder only when writing the plan.
Entry points
- Route handoff from
brainstorm-feature: write the plan and present it for the joint approval (step 9). - Route handoff from
estimate-feature: when the user asked for an estimate and only a writtendesign.mdexists, write the plan, callestimate-featurebefore the approval gate, and present the plan and estimate together. - Route handoff from
implement-task: a material decision found during implementation. Revise the opentasks.md, record the decision in its## Decision Log, reset the gate topending, present the revision for approval, and resumeimplement-taskafter re-approval. - Repair handoff (e.g.
estimate-featureasking for missing task detail in an existing plan): fix the plan, run the self-review, and return to the caller with the gate preserved or reset and the reason. Do not callestimate-featureor ask for approval, and never start implementation.
Process
- Read the design,
AGENTS.md, and related wiki pages. If application source exists, call the available Skill entry whose local name isread-codebase-contextto inspect affected source, callers, and tests; otherwise map planned files and interfaces from the design and state that callers and tests do not exist yet. Revise an open change'stasks.mdin place; new architectural work after a change is archived gets a new design and folder. Keep completed tasks and results historical; add new work as a new task only while the change is open. Extract only exact constraints from the design that bind more than one task; infer none from convention. - Map which files will be created or modified and what each is responsible for.
Follow existing patterns; do not unilaterally restructure. Before accepting a
proposed unit, apply
implement-task's## Implementation ladder, planning new code only at its last step. Every new file, abstraction, dependency, or configuration value must map to an approved requirement, and minimal design must not remove explicit behavior, trust-boundary validation, security, accessibility, or error handling that prevents data loss. - Split the work into small, ordered tasks with the fields in
references/tasks-template.md(read it now). Put contract and data changes before their callers and tests beside the behavior they verify. Map every approved edge case to a task and a specific check. If planning exposes an unresolved case that would change observable behavior, scope, an interface, a schema, or a protected boundary, stop and callbrainstorm-feature; leave only behavior-equivalent details forimplement-taskrulings. Add no tasks for speculative abstractions, and do not addreview-and-verifyor commit steps;implement-taskowns the final review. Plans describe intended behavior and interfaces, not code: include no function bodies or full test code. Include exact snippets only when the precise string, regex, config value, or contract shape is itself a requirement. - Give each task a meaningful
Verifycheck using the existing test runner and a failing test when it protects changed behavior. With no tests, use a repeatable check available in the project; do not add a test runner solely for the plan. Record the expected result, and mark a behaviorcannot verifywhen no check can establish it. For a source-less project, the first task bootstraps the runtime and first entry point the design specifies, with its verification; if the design does not establish them, callbrainstorm-feature. - Add
## Approval Gateand## Decision Logas the template shows. A newtasks.mdisStatus: pending; revisions follow the template's revision rule. - Save the complete plan with
## Design,## Global Constraints, and## Impact map(seven fields fromread-codebase-context's## Trace and record the impact). The folder is indexed only on approval (step 9). - Run the self-review below and fix issues inline.
- Do not estimate effort here. When the user explicitly requests an estimate,
call
estimate-featurebefore presenting the approval gate; otherwise present none. An estimate never authorizes implementation. - Before requesting approval or delivering a planning-only result, give a short
summary in the user's language with links to the written files: Goal;
Scope and impact; Tasks (count and ordered titles); Verification
(checks, naming any limit); Documentation (pages to update, or wiki not
applicable); Risks and decisions. Summarize the actual design and tasks,
not a second plan. State whether approval authorizes implementation or the
request stops at planning. Unresolved material decisions return to
brainstorm-feature; never present the plan as ready to implement. Apply the template's revision rule first: an existing plan that stays approved is summarized without a new approval request. Otherwise presentdesign.md,tasks.md, anydelta.md, and the requested estimate together and ask for one approval, then stop without editing application code. Revise the files in place until the user explicitly approves; then setStatus: approved, index the folder perusing-devkit's## Change lifecycle, and continue: callsetup-codebasefirst when the target has noAGENTS.mdor application source, thenimplement-task. That approval is the gate, so do not ask again. If the user limited the request to design or planning, record the approval and stop. End with theNext:block fromusing-devkit; for a pending gate it names the exact approval the user must give.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 19d ago Changed · -122 lines · -1 tokens per session 50a0efac053d
- 26d ago Changed · +70 lines · +12 tokens per session 5463284e31b9
- 1mo ago First seen · 184 lines · 32 tokens per session scan A 4197d0f5442a
plan-feature is a skill published in the GitHub repository asta-nguyen/kamehadb (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,882 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
plan-feature compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plan-featureasta-nguyen/kamehadb | Skill | 14 | 10d ago | Apache-2.0 | A | 43 | Claude Code, Codex |
| chromaNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 12 | Claude Code, Codex |
| backend-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 51 | Claude Code, Codex |
| database-migrationsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 61 | Claude Code, Kiro |
| postgres-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 45 | Claude Code, Kiro |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 12k | yesterday | CC0-1.0 | A | 116 | Claude Code, Codex |
| review-prsgoogleapis/mcp-toolbox | Skill | 17k | yesterday | Apache-2.0 | A | 162 | Claude Code, Codex |