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/atuljha23/holocron/commitgit clone --depth 1 https://github.com/atuljha23/holocronWhat 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 | $0.00030 | $0.00577 |
| Opus 5 | $0.00015 | $0.00289 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
commit 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.
What it actually says
/holocron:commit
Do these in order. Do not skip.
1. See what's staged
git status
git diff --cached
If nothing is staged, ask which files to stage. Do not run git add -A or git add . without an explicit green light — too easy to sweep in secrets or noise.
2. Quality gates
Detect the stack and run what exists (skip what doesn't, don't invent scripts):
- Node — if
package.jsonhas scripts:npm run lint,npm run typecheck(orcheck-types),npm test(or the narrowest subset that covers changed files). - Python —
ruff check .orflake8if present;pytest -q(or-kthe changed paths). - Go —
go vet ./...,go test ./.... - Rust —
cargo clippy,cargo test.
If any gate fails, stop. Do not commit. Report the failure to the user with the exact output. The user decides whether to fix or override (--no-verify).
3. Review the staged diff
Delegate a short review pass to @code-reviewer against the staged diff (not HEAD). If the reviewer flags a Blocker, stop and report before committing.
4. Draft the message
Use Conventional Commits. Match the repo's history style (check git log --oneline -20). Short subject (<72 chars), blank line, body only when the "why" isn't obvious from the diff.
Do not add marketing or emoji unless the repo's history uses them.
5. Commit
Use a HEREDOC to preserve formatting:
git commit -m "$(cat <<'EOF'
<type>(<scope>): <short subject>
<body: why this change, not what>
EOF
)"
6. Verify
Run git status and show the resulting commit with git log -1 --stat.
Flags
--no-verify: skip quality gates. Require the user's explicit instruction in the invocation — don't skip silently.--amend: only if explicitly requested by the user. Warn if the commit has been pushed.
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 · 62 lines · 0 tokens per session scan A c8e95545b052
commit is a command published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 577 once invoked, about $0.0002 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
autopilot
Autonomous session-orchestration loop with kill-switches (Phase C-1.b — all 10 kill-switches shipped).
brainstorm
Run a lightweight Socratic design dialogue (3-5 AUQ rounds) and write a spec markdown file before any implementation work. Use BEFORE /plan feature when scope/UX is ambiguous.
contract-version-bump
Classify and apply a version bump to a machine-readable contract (JSON Schema, API spec, config schema) — version literals, consumer compatibility, changelog entry, downstream drift.
reconcile
Reconcile learnings into .claude/rules/ proposals — on-demand version of session-end Phase 3.6.8.
spinout
Guided 5-step venture-spinout / sanitized-fork runbook (copy + fresh-init + SNAPSHOT-FREEZE) — interactive, not scripted.
go
Approve session plan and begin wave execution.