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 commitgit 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/commit)<a href="https://agentmods.dev/skills/rajitsaha/100xprism/commit"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/commit/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/commit"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.01534 |
| Opus 5.5 | $0.00007 | $0.00614 |
| Sonnet 5.5 | $0.00003 | $0.00307 |
| Haiku 4.5 | $0.00002 | $0.00153 |
Grade A, and why
commit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit — Gate → Stage → Commit
Quality gate runs FIRST. Do NOT commit if any gate fails. Do NOT ask for permission or skip the gate.
Phase 0 — Quality Gate (MANDATORY)
Check gate cache first — skip if it already passed for this exact tree state. The cache is keyed on a tree token (HEAD + tracked diff + untracked files), not a bare HEAD, so a dirty or rebased tree never reuses a stale pass:
TOKEN=$(python3 ~/100xprism/hooks/gate-pass.py --print 2>/dev/null)
CACHED=$(cat ~/.100xprism/gate-cache 2>/dev/null)
[ -n "$TOKEN" ] && [ "$CACHED" = "$TOKEN" ] && echo "Gate: skipped (already passed for this tree)" && GATE_DONE=true || GATE_DONE=false
If GATE_DONE=false: run the gate workflow. On pass, record it (same token the
gate-on-commit hook checks):
python3 ~/100xprism/hooks/gate-pass.py
Do NOT proceed until gate reports ✅ ALL GATES PASSED. If any gate fails → STOP, fix, clear cache, re-run gate.
Phase 1 — Review changes
PROJECT_ROOT=$(git rev-parse --show-toplevel)
cd "$PROJECT_ROOT"
git status
git diff --stat
git diff --name-only HEAD 2>/dev/null || true
Phase 2 — Update docs (if needed)
Based on what changed, update corresponding documentation:
| Changed files | Doc to update |
|---|---|
| API routes or handlers | API reference doc (README, project instruction file, or docs/) |
| CLI commands or flags | CLI reference doc |
| New features or config | README.md or project-equivalent |
| Removed files/features | Remove stale references from all docs |
.claude/commands/** |
No doc update needed |
Read the project instruction file for specific doc file paths. Skip if no docs are affected.
Phase 3 — Stage files
Stage only task-related files. Never stage .env, dist/, node_modules/, venv/, unrelated work:
git add -u
# Or stage specific files if -u picks up unrelated changes:
# git add path/to/file1 path/to/file2
git diff --staged --stat
Phase 4 — Write and create commit
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 · 192 lines · 17 tokens per session scan A 1b3dd47d75c3
commit is a skill published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 1,534 once invoked, about $0.0001 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
ax-extract-workflow
Reconstruct workflow behind a past coding-agent artifact using local ax sessions/commits/skills/tool traces. Use when asked how X was built.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
memorix-git-memory
Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.
feature
Full per-feature pipeline: implement → testloop → evaluator challenge → coder feedback → document → commit.
quick
/quick — Lightweight Feature Workflow.
undercover-mode
When contributing to public or open-source repositories where AI attribution should be hidden. Use when the user says "stealth mode," "undercover," "no AI attribution," "hide AI," "contribute anonymously," "clean commits," "no co-authored-by," or when working on repos where AI involvement should not be visible. Strips…