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/jamie-bitflight/git-project-xray-mcp/updategit clone --depth 1 https://github.com/Jamie-BitFlight/git-project-xray-mcpWrote 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/jamie-bitflight/git-project-xray-mcp/update)<a href="https://agentmods.dev/commands/jamie-bitflight/git-project-xray-mcp/update"><img src="https://agentmods.dev/badge/commands/jamie-bitflight/git-project-xray-mcp/update.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.01190 |
| Opus 5 | $0.00007 | $0.00595 |
| Sonnet 5 | $0.00003 | $0.00238 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade B, and why
gsd:update scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat "./.claude/get-shit-done/VERSION" How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provides a better update experience than raw npx get-shit-done-cc by showing version diff and changelog entries.
# Check local first (takes priority)
if [ -f "./.claude/get-shit-done/VERSION" ]; then
cat "./.claude/get-shit-done/VERSION"
echo "LOCAL"
elif [ -f ./.claude/get-shit-done/VERSION ]; then
cat ./.claude/get-shit-done/VERSION
echo "GLOBAL"
else
echo "UNKNOWN"
fi
Parse output:
- If last line is "LOCAL": installed version is first line, use
--localflag for update - If last line is "GLOBAL": installed version is first line, use
--globalflag for update - If "UNKNOWN": proceed to install step (treat as version 0.0.0)
If VERSION file missing:
## GSD Update
**Installed version:** Unknown
Your installation doesn't include version tracking.
Running fresh install...
Proceed to install step (treat as version 0.0.0 for comparison).
npm view get-shit-done-cc version 2>/dev/null
If npm check fails:
Couldn't check for updates (offline or npm unavailable).
To update manually: `npx get-shit-done-cc --global`
STOP here if npm unavailable.
If installed == latest:
## GSD Update
**Installed:** X.Y.Z
**Latest:** X.Y.Z
You're already on the latest version.
STOP here if already up to date.
If installed > latest:
## GSD Update
**Installed:** X.Y.Z
**Latest:** A.B.C
You're ahead of the latest release (development version?).
STOP here if ahead.
- Fetch changelog (same as fetch_changelog step)
- Extract entries between installed and latest versions
- Display preview and ask for confirmation:
## GSD Update Available
**Installed:** 1.5.10
**Latest:** 1.5.15
### What's New
────────────────────────────────────────────────────────────
## [1.5.15] - 2026-01-20
### Added
- Feature X
## [1.5.14] - 2026-01-18
### Fixed
- Bug fix Y
────────────────────────────────────────────────────────────
⚠️ **Note:** The installer performs a clean install of GSD folders:
- `commands/gsd/` will be wiped and replaced
- `get-shit-done/` will be wiped and replaced
- `agents/gsd-*` files will be replaced
(Paths are relative to your install location: `./.claude/` for global, `./.claude/` for local)
Your custom files in other locations are preserved:
- Custom commands not in `commands/gsd/` ✓
- Custom agents not prefixed with `gsd-` ✓
- Custom hooks ✓
- Your CLAUDE.md files ✓
If you've modified any GSD files directly, back them up first.
Use AskUserQuestion:
- Question: "Proceed with update?"
- Options:
- "Yes, update now"
- "No, cancel"
If user cancels: STOP here.
If LOCAL install:
npx get-shit-done-cc --local
If GLOBAL install (or unknown):
npx get-shit-done-cc --global
Capture output. If install fails, show error and STOP.
Clear the update cache so statusline indicator disappears:
If LOCAL install:
rm -f ./.claude/cache/gsd-update-check.json
If GLOBAL install:
rm -f ./.claude/cache/gsd-update-check.json
╔═══════════════════════════════════════════════════════════╗
║ GSD Updated: v1.5.10 → v1.5.15 ║
╚═══════════════════════════════════════════════════════════╝
⚠️ Restart Claude Code to pick up the new commands.
[View full changelog](https://github.com/glittercowboy/get-shit-done/blob/main/CHANGELOG.md)
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.
- 4d ago First seen · 201 lines · 14 tokens per session scan B c9b400daa55f
gsd:update is a command published in the GitHub repository Jamie-BitFlight/git-project-xray-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 1,190 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It comes from a forked repository.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.