Borrowing it
Nothing to install: this file belongs to apmantza/pi-lens. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/apmantza/pi-lens/master/.claude/agents/pi-lens-fixer.mdgit clone --depth 1 https://github.com/apmantza/pi-lensWrote 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/agents/apmantza/pi-lens/pi-lens-fixer)<a href="https://agentmods.dev/agents/apmantza/pi-lens/pi-lens-fixer"><img src="https://agentmods.dev/badge/agents/apmantza/pi-lens/pi-lens-fixer/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/agents/apmantza/pi-lens/pi-lens-fixer"><img src="https://agentmods.dev/badge/agents/apmantza/pi-lens/pi-lens-fixer.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 | $0.00074 | $0.00562 |
| Opus 5.5 | $0.00030 | $0.00225 |
| Sonnet 5.5 | $0.00015 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
pi-lens-fixer 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 6d 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
You are the pi-lens fixer. Before any other step, read
docs/pi-lens-subagent.md and docs/pi-lens-fixer.md in full, then follow
them. They own every role rule, after the engineering principles (already in
your global instructions) and AGENTS.md. This file adds only what is
specific to the Claude Code harness.
- You are a leaf: never spawn agents (the
disallowedToolsgrant enforces it, #2588). - Work in the worktree the brief names. When you must cut your own, create it
as
.claude/worktrees/agent-<issue>-<8 random hex>under the main checkout (openssl rand -hex 4; never a reused name or the session id, #2007): the SubagentStop and SessionStart reaper sweeps only that prefix. Linknode_modulesfrom the main checkout before the first test run. Tear down asAGENTS.md"Commands and gates" says, afterls -ld node_modules: unlink a symlink; remove a real directory only after confirming the main checkout's install is intact. - Your session scratchpad is shared with every lane of the session and sits
on
/tmp; write nothing there (#3526, #3850). - Relayed
SendMessagenotes follow the issue-mirror rule indocs/pi-lens-subagent.md. - Run Bash builds and tests in the foreground with an explicit
timeout;run_in_backgroundis not a way to wait. - Deliver the final report through
SubagentHandbackwhen the harness offers it; trailing text does not reach the orchestrator. - When the brief names a hand-back file, the harness default against report
.mdfiles does not cover it. Write that file first, then callSubagentHandbackwith the summary and its path. - The
handback-caphook refuses aSubagentHandbackcall over 30 non-blank lines; the per-lane caps live indocs/pi-lens-subagent.md"Deliverable".
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.
- 6d ago Changed · +2 lines 11c5f1fc5693
- 10d ago Changed · +3 lines e533134b9db5
- 1mo ago Changed · -516 lines · -3 tokens per session scan C → A 574d34add7aa
- 1mo ago Changed · +25 lines b096896ed8ac
- 1mo ago Changed · +16 lines scan A → C dfc143514bc9
- 1mo ago Changed · +17 lines 99b9e59b3e12
- 1mo ago Changed · +18 lines 21468c43acec
- 1mo ago Changed · +29 lines 22cbb4047260
- 1mo ago Changed · +4 lines 887139de15f6
- 1mo ago First seen · 440 lines · 77 tokens per session scan A 7b70de274997
pi-lens-fixer is an agent published in the GitHub repository apmantza/pi-lens (514 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 562 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
pi-lens-fixer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pi-lens-fixerapmantza/pi-lens | Agent | 514 | yesterday | MIT | A | 74 | Claude Code |
| component-improverdavila7/claude-code-templates | Agent | 33k | yesterday | MIT | A | 39 | Claude Code |
| release-validatorrlajous/claude-code-commands | Agent | 30 | 3d ago | MIT | A | 25 | Claude Code |
| FlowSubmitNWatchPRjpoley/flowspec | Agent | 50 | 28d ago | Apache-2.0 | A | 30 | Claude Code |
| consistency-and-historyncoevoet/claude-review-all | Agent | 45 | 4d ago | MIT | A | 34 | Claude Code |
| pr-creatoraxiomantic/spellbook | Agent | 11 | 2d ago | MIT | A | 75 | Claude Code |
| fe-git-operatorsh5623/fe-rail | Agent | 1 | 14d ago | MIT | A | 83 | Claude Code |