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 skills add rajitsaha/100xprism --skill pair-loopgit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/skills/rajitsaha/100xprism/pair-loop)<a href="https://agentmods.dev/skills/rajitsaha/100xprism/pair-loop"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/pair-loop/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/skills/rajitsaha/100xprism/pair-loop"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/pair-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 126 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00053 | $0.01717 |
| Opus 5.5 | $0.00021 | $0.00687 |
| Sonnet 5.5 | $0.00011 | $0.00343 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
pair-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pair-Loop — Coder <-> Reviewer Handoff
Runs a formal review loop between a coder and a reviewer (default: you as coder,
Codex as reviewer — swap via ~/.100xprism/config.json's pair_loop section).
Three vendors are supported — claude, codex, cursor — as either role.
Each round is recorded in HANDOFF.md and self-instrumented into a cost
manifest the token dashboard reads. Do NOT ask for permission to start or to
run rounds — only stop for the outcomes listed in "When to stop" below.
Step 1 — Start
PROJECT_ROOT=$(git rev-parse --show-toplevel)
cd "$PROJECT_ROOT"
python3 ~/100xprism/scripts/pair-loop.py start --task "<one-line task description>"
If this fails with a "dirty" error, commit or stash first — do not force-start
on uncommitted work. Save the printed run_id, handoff_path, max_rounds,
coder, and reviewer — you'll pass run_id to every subsequent command.
Step 2 — Budget check (before every round)
python3 ~/100xprism/scripts/pair-loop.py budget-check --run "$RUN_ID"
Exit code 2 means the per-run budget cap is hit — STOP and ask the user
whether to continue or stop; do not proceed to another round silently. Exit
code 0 with "level": "warn" in the output means print a one-line warning
and continue.
Step 3 — Coder round
Implement the task (or address the reviewer's findings from the prior round). Run the project's quick checks (tests + lint) before recording the round. Do not commit — leave all changes in the working tree so review diffs stay accurate across rounds; commit only in Step 5 (PR phase). Then:
python3 ~/100xprism/scripts/pair-loop.py coder-done --run "$RUN_ID" \
--summary "<what you implemented/fixed, files touched, how you verified it>" \
--findings-addressed <N>
Step 4 — Reviewer round
python3 ~/100xprism/scripts/pair-loop.py review --run "$RUN_ID"
This shells out to the configured reviewer and returns
{"verdict":, "findings": [...], "fallback_used":, "reviewer_tool":, "reviewer_model":, "same_model_conflict":}.
reviewer_tool is the vendor that actually ran — with three vendors, do not
assume it equals pair_loop.reviewer; check it, especially when
fallback_used is true.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 130 lines · 53 tokens per session scan A b2f372fff87f
pair-loop is a skill published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 1,717 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
revert
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level. Use when the user asks to 'revert this track', 'undo a phase', 'revert task X', or says 'roll back the last task', 'undo this work'.
upload
Pre-upload gate for track handoff. Verifies review status, HLD approvals, deploy checklist, and validator chain before git upload or PR submission.