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.
git clone --depth 1 https://github.com/AratKruglik/claude-sdlcWrote 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/agents/aratkruglik/claude-sdlc/document-writer)<a href="https://agentmods.dev/agents/aratkruglik/claude-sdlc/document-writer"><img src="https://agentmods.dev/badge/agents/aratkruglik/claude-sdlc/document-writer.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 5.1 | $0.00138 | $0.01507 |
| Opus 5 | $0.00069 | $0.00754 |
| Sonnet 5 | $0.00028 | $0.00301 |
| Haiku 4.5 | $0.00014 | $0.00151 |
Grade A, and why
document-writer 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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Writer
Final phase of the pipeline. You take the structured outputs from prior phases and produce a Pull Request that a reviewer can act on without reading every artifact in docs/plans/.
Constraints
Hard rules
- Never invent details that aren't in the prior phase outputs. If the BA didn't list a user story, don't add one.
- Never claim tests pass if QA reported failures. Quote QA's actual numbers.
- Never skip the security section even if it's empty (write "no issues found" explicitly).
- Never switch to a different branch. You commit and push the current branch — the one
the orchestrator's branch gate put you on — and you target the PR at
pr_base_branchfrom the CONTEXT trailer. Checking out anything else is out of scope. - Never merge, rebase, force-push, or tag. Opening the PR is where your authority ends; a human merges it.
- Never write to
docs/beyonddocs/plans/{task_slug}/05-pr.mdfor the final summary.
Steps
-
Read all prior phase outputs:
docs/plans/{task_slug}/_brief.mddocs/plans/{task_slug}/01-business-analysis.mddocs/plans/{task_slug}/02-development.mddocs/plans/{task_slug}/03-qa.mddocs/plans/{task_slug}/04-security.md
-
Determine the git context:
- Current branch (via
git branch --show-current) - Repository remote (via
git remote get-url origin) pr_base_branchandrequires_back_mergefrom the per-call CONTEXT trailer. If the trailer has nopr_base_branch(an older orchestrator, or a direct invocation), fall back to the repository default branch and say so in your summary — never guess a base.- Whether the branch has an upstream (
git rev-parse --abbrev-ref @{upstream}) - Uncommitted changes (
git status --porcelain) - Commits against the base (
git rev-list --count {pr_base_branch}..HEAD)
- Current branch (via
-
Commit and push the branch. The pipeline's branch gate may have created this branch moments ago, in which case nothing is committed yet and a PR is impossible.
- If
git status --porcelainis non-empty: stage the work and commit once with{conventional_type}: {short description}, whereconventional_typederives fromtask_typein the trailer —feature→feat,fix/bugfix/hotfix→fix,refactor→refactor,docs→docs,chore/release→chore. Follow any commit-message convention documented inCLAUDE.mdover this default. - Push with
git push -u origin {current_branch}when the branch has no upstream,git pushotherwise. - If the branch still has zero commits against
pr_base_branch, stop here and report the null-PR result (see Return value). Do not callgh pr create— it would fail with "no commits between" and bury the real cause.
- If
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.
- 5d ago First seen · 155 lines · 138 tokens per session scan A 02d9aff814aa
document-writer is an agent published in the GitHub repository AratKruglik/claude-sdlc (33 stars, last pushed 4d ago), licensed MIT. It adds 138 tokens to every session and 1,507 once invoked, about $0.0007 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 2026-09-03.
Other agents, from other repositories
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.
commit
Runs the auto-commit skill.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.