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/xrensiu/claude-code-forge/pushgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWhat 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 | $0.00008 | $0.00501 |
| Opus 5 | $0.00004 | $0.00251 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
push 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.
What it actually says
Auto Commit and Push
Automatically stage all changes, create a commit with AI-generated message, and push to remote.
Parameters
$ARGUMENTS: Custom commit message (optional). If not provided, generate based on changes.
Instructions
-
Check for changes:
- Run
git statusto see if there are any changes - If no changes (working tree clean), inform user and stop
- Run
-
Get current branch:
- Run
git branch --show-currentto get current branch name - Check if branch has upstream with
git rev-parse --abbrev-ref @{upstream}
- Run
-
Analyze changes:
- Run
git diffandgit diff --stagedto see all changes - Run
git status --porcelainto see untracked files
- Run
-
Generate commit message:
- If
$ARGUMENTSis provided, use it as the commit message - Otherwise, analyze the changes and generate a concise commit message following conventional commits format:
feat:for new featuresfix:for bug fixesrefactor:for refactoringdocs:for documentationstyle:for formatting changestest:for testschore:for maintenance tasks
- If
-
Stage and commit:
git add -A git commit -m "${COMMIT_MESSAGE} Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>" -
Push to remote:
- If upstream exists:
git push - If no upstream:
git push -u origin ${BRANCH_NAME}
- If upstream exists:
-
Report results:
- Show the commit hash and message
- Show push result
- If any step fails, show error and stop
Error Handling
- If
git addfails, show error - If
git commitfails (e.g., pre-commit hook), show the error and attempt to fix if files were auto-modified - If
git pushfails, show error and suggestgit pull --rebaseif needed
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 · 62 lines · 8 tokens per session scan A 6418e8c89f44
push is a command published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 501 once invoked, about $0.0000 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.