Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/tomdwipo/claude-soul/do-implementationgit clone --depth 1 https://github.com/tomdwipo/claude-soulWrote 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/commands/tomdwipo/claude-soul/do-implementation)<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/do-implementation"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/do-implementation.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.03839 |
| Opus 5 | $0.00000 | $0.01920 |
| Sonnet 5 | $0.00000 | $0.00768 |
| Haiku 4.5 | $0.00000 | $0.00384 |
Grade A, and why
do-implementation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
do implementation Command
read all lines from .docs/year(YYYY)/month(MM)/day(DD)/{number-in-DD-folder(01)}-$ARGUMENTS/$ARGUMENTS-spec.md and .docs/year(YYYY)/month(MM)/day(DD)/{number-in-DD-folder(01)}-$ARGUMENTS/$ARGUMENTS-implementation-plan.md first for context. do a detailed step-by-step implementation new feature from document .docs/year(YYYY)/month(MM)/day(DD)/{number-in-DD-folder(01)}-$ARGUMENTS/$ARGUMENTS-spec.md and must follow the implementation plan at .docs/year(YYYY)/month(MM)/day(DD)/{number-in-DD-folder(01)}-$ARGUMENTS/$ARGUMENTS-implementation-plan.md. you have to be on that track in the implementation phase. Ensure all steps are completed before proceeding to the next feature. add the necessary unit tests for each step or follow the testing considerations in the implementation plan. don't add any comments in real code except TODO comments. update or create the Acceptance Criteria (AC) if it doesn't exist at .docs/year(YYYY)/month(MM)/day(DD)/{number-in-DD-folder(01)}-$ARGUMENTS/ to reflect the new feature's success metrics. run ./gradlew build for specific feature related the code changes after all done implementation the code before update Acceptance Criteria (AC). think hard and provide a comprehensive implementation plan with before/after code examples for each step. dont create other file EXCEPT:
- the Acceptance Criteria (AC) file (update or create)
- the Roborazzi baselines +
.figma.pngreference siblings under.docs/screen/{module}/(see §Roborazzi Verification) *ScreenshotTest.ktsource files when the PR touches UI — these are the verification artifact, not "other files". A baseline cannot exist without a test, and the reviewer needs to see the visual change in the PR diff.
If touch UI ⇒ MUST ship *ScreenshotTest.kt. Any PR that modifies a *Screen.kt, a core-ui/ Composable, or any other renderable code MUST include the corresponding *ScreenshotTest.kt + baseline PNG in the same commit. Reviewer needs to compare in PR diff; a ⚠️ deferred line in the AC is not a substitute. For screens with heavy ViewModel deps (Dashboard, multi-VM flows), follow the repo pattern of MIRRORING the visible layout in the test rather than instantiating the real Composable — see ChatUnavailableBottomSheetScreenshotTest.kt for the canonical shape.
max 20000 characters for Acceptance Criteria (AC) file. If the result exceeds 20000 characters, leave it as is — do NOT truncate, summarize, or drop sections to fit the limit.
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.
- 4d ago First seen · 264 lines · 0 tokens per session scan A 5a63a020bed1
do-implementation is a command published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,839 tokens. 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.