A command that scans a codebase and its recent Git history to draft a technical specification and a list of possible upcoming plans. Git history records how the project’s files have changed over time.

Use it to map a module’s files, exported code, data types, routes, and state flow, or to find TODO, FIXME, HACK, and XXX markers and recent code churn.

It turns existing code, unfinished-work markers, and recent changes into documentation drafts, reducing the need to start specifications and planning notes from blank pages.

scan — Command by MedAdemBHA

Install

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.

agentmods

npx agentmods add commands/medadembha/docflow/scan

Clone the repo

git clone --depth 1 https://github.com/MedAdemBHA/docflow

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 466 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00016	$0.00466
Opus 5	$0.00008	$0.00233
Sonnet 5	$0.00003	$0.00093
Haiku 4.5	$0.00002	$0.00047

Measured 2d ago against content hash 7ce3a6c6e06b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan 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 2d 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.

commands/scan.md · 28 lines

What it actually says

Turn the actual codebase into doc drafts (not blank templates). Two generators; the draft is then verified + trimmed by you.

Spec from a module

bash "${CLAUDE_PLUGIN_ROOT}/scripts/docflow-spec.sh" <code-path> --target "$CLAUDE_PROJECT_DIR" --docs-root <DOCS_ROOT>

Scans the path → writes <DOCS_ROOT>/specs/(mmm-yy)-<name>.md pre-filled with: source file list, exported symbols (Architecture), interfaces/types/enums (Data), string paths + HTTP verbs (API), hooks/state (Flow). Add --stdout to preview without writing. Won't overwrite an existing spec.

After generating: verify the auto lists, group exports into the real component/service map, confirm which paths are real endpoints, and fill the Risks section (heuristics can't infer it).

Plan candidates from repo signal

bash "${CLAUDE_PLUGIN_ROOT}/scripts/docflow-plan.sh" --target "$CLAUDE_PROJECT_DIR" --docs-root <DOCS_ROOT> --days 30

Scans TODO/FIXME/HACK/XXX markers + git churn (last N days) → writes <DOCS_ROOT>/plans/upcoming/(mmm-yy)-candidates.md. It will not overwrite an existing candidates file unless --force is passed. Set SCAN_DIR=src to limit scope.

After generating: triage each candidate into critical/now/next/later.md, then delete the candidates file. Markers in high-churn areas → likely critical/now.

Rules

These produce drafts. Never ship an unverified auto-spec — the agent/dev curates first.
Re-run after big code changes to refresh the discovered surface.
Regenerate INDEX.md afterward: bash "${CLAUDE_PLUGIN_ROOT}/scripts/docflow-map.sh" "$CLAUDE_PROJECT_DIR/<DOCS_ROOT>".
Validate before reporting completion: bash "${CLAUDE_PLUGIN_ROOT}/scripts/docflow-validate.sh" --target "$CLAUDE_PROJECT_DIR".

Changes

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.

2d ago First seen · 28 lines · 16 tokens per session scan A 7ce3a6c6e06b

Subscribe to this mod's changes

scan is a command published in the GitHub repository MedAdemBHA/docflow (41 stars, last pushed 17d ago), licensed MIT. It adds 16 tokens to every session and 466 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.

Git and workflow Planning Writing and docs ai-agents claude-code-plugin codex-plugin documentation

scan

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Spec from a module

Plan candidates from repo signal

Rules

What this file has done since we first saw it

Other commands, from other repositories

search

review-renovate

monitor-ci

/add-claude-rule

implement-regression-tests

plan-regression-tests