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/chrisdev1187/claude-code-forge/new-sprintgit clone --depth 1 https://github.com/chrisdev1187/claude-code-forgeWhat 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 | $0.00000 | $0.00376 |
| Opus 5 | $0.00000 | $0.00188 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
new-sprint 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 yesterday.
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
/new-sprint — Open Next Sprint
Run this at the start of a new sprint to create the gate file and update state.
Steps
-
Read
docs/sprints/CURRENT_SPRINT.md— get current sprint number N -
The next sprint is N+1
-
Create
docs/sprints/sprint-[N+1]-gate.mdby filling in all 4D sections:D1 — Define:
- Exact problem in 1-2 sentences
- "Done means" — 2-3 specific testable outcomes
- Git tag target
D2 — Detail:
- All dependencies (credentials, APIs, services)
- Edge cases and how to handle each
- Token budget per operation
D3 — Direct:
- Step-by-step sequence (numbered)
- Success criterion per step
D4 — Dialogue:
- What could go wrong + mitigation
- Gaps to resolve before starting
- Human review checkpoint
-
Get explicit approval on D1-D4 before writing any code
-
Update
docs/sprints/CURRENT_SPRINT.mdto N+1:echo "N+1" > docs/sprints/CURRENT_SPRINT.md -
Commit the gate file:
rtk git add docs/sprints/sprint-[N+1]-gate.md docs/sprints/CURRENT_SPRINT.md rtk git commit -m "docs: open sprint N+1 gate — [brief description]"
Gate rule
The git pre-commit hook will block all commits if the current sprint's gate file is missing. The gate file must exist BEFORE any implementation work begins.
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.
- yesterday First seen · 48 lines · 0 tokens per session scan A 7638e04ba4b0
new-sprint is a command published in the GitHub repository chrisdev1187/claude-code-forge (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 376 tokens. 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
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
new
Creates a new item in a module that supports the new capability.
card
Open one self-contained OverClick card.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.