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/genai-jerry/claude-software-factory/implementergit clone --depth 1 https://github.com/genai-jerry/claude-software-factoryWrote 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/genai-jerry/claude-software-factory/implementer)<a href="https://agentmods.dev/commands/genai-jerry/claude-software-factory/implementer"><img src="https://agentmods.dev/badge/commands/genai-jerry/claude-software-factory/implementer.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 | $0.00015 | $0.01535 |
| Opus 5 | $0.00008 | $0.00767 |
| Sonnet 5 | $0.00003 | $0.00307 |
| Haiku 4.5 | $0.00002 | $0.00153 |
Grade A, and why
implementer 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 yesterday.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Implementer of the Software Factory (see FACTORY.md).
Input: a task sub-issue number labelled factory:ready: $ARGUMENTS
Step 0 — load the repo profile
Read .factory/profile.json at the repository root. It is the authoritative
source for this repo's stack, branches, commands (test/build/lint),
conventions, qa_notes and gotchas. Everything below refers to those
values. If the file is missing or unparseable: stop, comment on the task
issue, apply factory:blocked — a factory repo must have a profile.
Step 0a — resolve the integration and epic branches
Nothing this factory writes reaches the default branch directly. Every
implementation PR lands first on the epic's own branch (FACTORY.md §6b) — or,
for an epic without one, on the integration branch, the org's staging or
test branch — and only a promotion PR reaches branches.default
(FACTORY.md §6a). Resolve both before you branch:
- Read
.github/factory-branches.json, the org's branch policy. Treat a missing file as{"staging": "staging", "required": true, "auto_create": true, "epics": false}; treat a missingepicskey asfalse. - The integration branch's name is the profile's
branches.stagingwhen that is a non-null string (a repo whose branch is called something else), else the policy'sstaging. - The step is required unless the policy sets
required: false.- Required: never base your PR on
branches.default. If the branch you resolve below does not exist on the remote and the policy'sauto_createis notfalse, cut it frombranches.default(git push origin origin/<default>:refs/heads/<branch>) and say so in the PR body. Ifauto_createisfalseand the branch is missing: stop, comment naming the branch that has to exist, applyfactory:blocked. required: false: the pre-policy fallback — the profile'sbranches.stagingwhen it names one, elsebranches.default.
- Required: never base your PR on
- Epic branch (FACTORY.md §6b): when the policy's
epicsistrue, your epic's branch isfactory/epic-<epic-issue-number>— the epic issue number is the leading number of the change folder (openspec/changes/<epic-issue-number>-<slug>/). Check whether it exists on the remote (git ls-remote --exit-code --heads origin factory/epic-<n>); do not create it yourself.- It exists: that is your base branch. It holds the approved spec and design, so read the change folder from it.
- It does not exist: this epic was already past gate G2 when the
policy was flipped on, so it finishes on the routing it started with
(§6b) — the base branch is the integration branch, as with
epics: false. Its tasks may already have merged there, which is exactly why a late epic branch would be wrong. Say which case you are in in the PR body.
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.
- yesterday Changed · +18 lines e1b16a380261
- 5d ago First seen · 93 lines · 15 tokens per session scan A a08afa20332b
implementer is a command published in the GitHub repository genai-jerry/claude-software-factory (2 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,535 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 2026-08-31.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.