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/medadembha/docflow/product-specgit clone --depth 1 https://github.com/MedAdemBHA/docflowWrote 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/medadembha/docflow/product-spec)<a href="https://agentmods.dev/commands/medadembha/docflow/product-spec"><img src="https://agentmods.dev/badge/commands/medadembha/docflow/product-spec.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 | $0.00017 | $0.00807 |
| Opus 5 | $0.00009 | $0.00404 |
| Sonnet 5 | $0.00003 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
product-spec 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow this prompt spec to create a docflow product spec from this source:
$ARGUMENTS
Rules
- If the source is empty, ask for one short feature brief or code path and stop.
- Product specs are WHAT docs: user behavior, user value, capabilities, scope.
- Keep HOW details out of
product-spec/; put implementation notes inspecs/follow-ups. - Treat code as evidence, not product truth. If behavior or user intent is unclear, write
TBD. - Do not overwrite an existing product spec blindly. If a target file exists, merge new facts into the right sections.
- Keep output lean: tables and bullets, no filler.
Steps
- Find the docs root:
- Read
docflow.jsonfrom$CLAUDE_PROJECT_DIRif present and usedocsRoot. - Otherwise use
docs.
- Read
- Read:
<DOCS_ROOT>/README.md<DOCS_ROOT>/NAMING.md${CLAUDE_PLUGIN_ROOT}/templates/product-spec/00-overview.md${CLAUDE_PLUGIN_ROOT}/templates/product-spec/NN-topic.md
- Inspect the source:
- If
$ARGUMENTSis a real file or directory, read the relevant README, package metadata, route/component filenames, exported names, and nearby tests. - If
$ARGUMENTSis prose, use it as the source brief.
- If
- Choose the target:
- Use
<DOCS_ROOT>/product-spec/00-overview.mdwhen the request describes the whole app, onboarding, project purpose, or missing overview content. - Otherwise create/update the next stable module doc:
<DOCS_ROOT>/product-spec/NN-<slug>.md. - Pick
NNas the next unused two-digit number inproduct-spec/.
- Use
- Write the product spec:
- For overview docs, include app name, type, stack if known, users, and core modules.
- For module docs, include purpose, key actions, business value, links, and known constraints.
- Use
TBDinstead of guessing missing users, owner, business value, or behavior.
- Add cross-links:
- Link to related
specs/docs if they already exist. - Link to related
plans/features/docs if they already exist. - Leave
TBDlinks when follow-up docs do not exist yet.
- Link to related
- Update
<DOCS_ROOT>/README.mdso the new product spec is discoverable. - If implementation details were discovered but no matching spec exists, report the needed
specs/(mmm-yy)-<topic>.mdfollow-up. - Regenerate the docs map:
If the target repo does not havebash "$CLAUDE_PROJECT_DIR/scripts/docflow-map.sh" "$CLAUDE_PROJECT_DIR/$DOCS_ROOT"scripts/docflow-map.sh, use:bash "${CLAUDE_PLUGIN_ROOT}/scripts/docflow-map.sh" "$CLAUDE_PROJECT_DIR/$DOCS_ROOT" - Run link check if available:
bash "$CLAUDE_PROJECT_DIR/scripts/check-links.sh" "$CLAUDE_PROJECT_DIR/$DOCS_ROOT"
- Run validation if available:
bash "$CLAUDE_PROJECT_DIR/scripts/docflow-validate.sh" --target "$CLAUDE_PROJECT_DIR"
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 · 73 lines · 17 tokens per session scan A 318046873be9
product-spec is a command published in the GitHub repository MedAdemBHA/docflow (41 stars, last pushed 19d ago), licensed MIT. It adds 17 tokens to every session and 807 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
search
Search OpenDocu local versioned official docs using explicit library keywords.
adr-supersede
Create a new ADR that supersedes an existing one.
adr-update
Update an existing ADR (status, content, or metadata).
sdlc-implement
Standalone issue implementation with Ralph Loop — implements a single Linear issue or free-form spec using fullstack-engineer + self-correcting retry loop.
sdlc
Master orchestrator for the complete 5-phase SDLC pipeline. Runs all phases sequentially with approval gates and handoffs between each phase. Organizes artifacts into handoffs/, docs/, and projects/ directories.
to-issues
Create one Linear issue per slice from an existing scope.json. Run standalone to (re)create issues without rerunning the full Plan phase. Falls back to docs/issues.md if Linear MCP is unavailable.