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/atuljha23/holocronWrote 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/atuljha23/holocron/permission-tune)<a href="https://agentmods.dev/commands/atuljha23/holocron/permission-tune"><img src="https://agentmods.dev/badge/commands/atuljha23/holocron/permission-tune/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/atuljha23/holocron/permission-tune"><img src="https://agentmods.dev/badge/commands/atuljha23/holocron/permission-tune.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00582 |
| Opus 5 | $0.00022 | $0.00291 |
| Sonnet 5 | $0.00009 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
permission-tune 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 10d 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
/holocron:permission-tune
Two files to inspect:
- User scope:
~/.claude/settings.json - Project scope:
.claude/settings.json(and.claude/settings.local.json, if present)
Steps
- Read the existing permissions from the relevant scope (
$ARGUMENTSselects; default: both). - Parse the
allowanddenyarrays (they may not exist). - Walk the recent conversation history surface this tool sees (or, if not available, ask the user which commands they find themselves approving repeatedly).
- Against the existing allowlist, identify:
- Safe read-only commands that are approved often but not on the allowlist (
git status,git diff,git log,ls,cat,grep,rg,find,fd,wc,head,tail,node <script>,python -c,pytest,npm test,go test,cargo test). - Dangerous commands that aren't on the denylist (
rm -rf *,git push --force *,git reset --hard *,npm publish,gh release *,curl | sh,wget | sh,sudo *,brew uninstall *).
- Safe read-only commands that are approved often but not on the allowlist (
- Propose a patch to
settings.json— show the exact JSON to add. Do not write the file automatically; the user approves the patch.
Output format
## Current state
- allow: <N entries>
- deny: <N entries>
## Proposed allowlist additions (safe, high-frequency)
- "Bash(git status:*)"
- "Bash(rg:*)"
- ...
## Proposed denylist additions (dangerous defaults)
- "Bash(rm -rf:*)"
- "Bash(git push --force:*)"
- ...
## Patch to apply
```json
{
"permissions": {
"allow": [ ... ],
"deny": [ ... ]
}
}
After this: use /update-config or edit settings.json by hand.
## Do not
- Do not rewrite `settings.json` silently.
- Do not broaden permissions to `"Bash(*)"` — that defeats the point.
- Do not add a command to both allow and deny. If you're torn, it belongs in `deny`.
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.
- 10d ago First seen · 59 lines · 43 tokens per session scan F f64e40e0b1cb
permission-tune is a command published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 582 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
learn
Learn Claude Code best practices and capture lessons into persistent memory.
insights
Surface patterns from your pro-workflow learnings and session history.
wiki
Build, query, and maintain long-lived knowledge bases. Each wiki = markdown folder + SQLite FTS5 shadow index. Survives sessions, indexes auto-load on SessionStart.
handoff
Generate a structured handoff document that another Claude session (or your future self) can consume immediately to continue where you left off.
commit
Create a well-crafted commit after running pro-workflow quality checks.
skill-optimize
Train a skill's SKILL.md by running a SkillOpt-flavored offline loop over accumulated learn-rule corrections.