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/sanmak/specops/pushgit clone --depth 1 https://github.com/sanmak/specopsWhat 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 | $0.00000 | $0.00554 |
| Opus 5 | $0.00000 | $0.00277 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00055 |
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 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Push the current branch to remote after validating all pre-push checks pass.
Instructions
Follow these steps precisely.
Step 1: Check current state
Run git status to confirm the working tree. If there are uncommitted changes (modified or untracked files), warn the user: "There are uncommitted changes. Run /commit first or commit manually before pushing." and stop.
Step 2: Check if there is anything to push
Run git log @{upstream}..HEAD --oneline 2>/dev/null to see unpushed commits.
If the command fails (no upstream set), note that we will push with -u to set upstream tracking.
If there are no unpushed commits and upstream exists, inform the user "Already up to date with remote -- nothing to push" and stop.
Step 3: Run pre-push validation
Before pushing, proactively run the same checks the pre-push hook will run, so we can fix issues before they block the push:
python3 generator/validate.py-- platform validationshasum -a 256 -c CHECKSUMS.sha256-- checksum verificationpython3 generator/generate.py --all && git diff --exit-code platforms/ skills/ .claude-plugin/-- generated files freshnesspython3 tests/check_schema_sync.py-- schema structurebash scripts/run-tests.sh-- full test suitenpx markdownlint-cli2 "core/**/*.md" "docs/**/*.md" ".claude/commands/**/*.md" "README.md" "CLAUDE.md" "QUICKSTART.md" "CONTRIBUTING.md" "CHANGELOG.md"-- markdown lint (skip if npx not available)
If any check fails:
- Report which check failed and the error output
- If the failure is fixable (stale generated files, stale checksums), explain what the user needs to do
- Do NOT push. Stop and let the user fix the issue.
Step 4: Push
Determine the current branch: git rev-parse --abbrev-ref HEAD
If the branch has an upstream, run:
git push
If the branch does not have an upstream, run:
git push -u origin <branch-name>
Do NOT use --no-verify -- let the pre-push hook run normally.
If the push fails, report the error to the user.
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 First seen · 59 lines · 0 tokens per session scan A 22b144da2557
push is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 554 tokens. 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
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].
ijfw-metrics
Show IJFW token / cost / session metrics over a time window. Reads .ijfw/metrics/sessions.jsonl via the ijfwmetrics MCP tool.
analyze
在任务生成后，对 spec.md、plan.md 和 tasks.md 进行只读的一致性与质量分析。.
review-pr
Fetch a pull request diff, run code-reviewer analysis, translate findings to owner voice, and post a single batched inline GitHub review.
rea
Print REA session status — autonomy level, HALT state, policy profile, and recent audit entries.