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 skills/rbah31/claude-code-workflow/full-sprintnpx skills add rbah31/claude-code-workflow --skill full-sprintgit clone --depth 1 https://github.com/rbah31/claude-code-workflowWrote 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/rbah31/claude-code-workflow/full-sprint)<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/full-sprint"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/full-sprint.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 | $0.00079 | $0.01475 |
| Opus 5 | $0.00039 | $0.00737 |
| Sonnet 5 | $0.00016 | $0.00295 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
full-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 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.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Sprint Execution
You are orchestrating a complete sprint cycle. Each phase runs in an
isolated claude -p session for context isolation — the review
MUST NOT have the build context (it biases the review).
IMPORTANT: This skill automates the same phase-by-phase workflow as
the manual sprint cycle. Quality comes from context isolation, not from
running everything in one session. Each phase runs via claude -p --dangerously-skip-permissions so all hooks fire (Stop runs tests,
PostToolUse scans secrets, PreToolUse blocks denylisted commands and
destructive git ops).
Step 1 — Load context
Read briefs/sprint-directive.md for the sprint scope and type.
Read .claude/CLAUDE.md to get the project name and context.
Step 2 — Determine sprint number
Find the highest sprint number in tasks/sprints/ and use N+1.
Create the directory: tasks/sprints/sprint-XX/
Step 3 — Execute phases
For each phase, run a separate claude -p session via Bash:
claude -p --dangerously-skip-permissions \
"You are working on [project name]. \
Read .claude/CLAUDE.md for project conventions. \
Read .claude/skills/[skill]/SKILL.md and follow its instructions exactly. \
Input: [input file path]. \
Save output to tasks/sprints/sprint-XX/[output file]. \
Run tests before declaring done."
Why claude -p without --bare: full hook enforcement applies — the
Stop hook runs tests, PostToolUse scans for secrets, PreToolUse blocks
denylisted commands and destructive git operations. The CLAUDE.md, rules,
and skills load automatically, so the agent gets the full project context
without us having to inline everything in the prompt.
The previous v3.x recommendation to use --bare for "~10x SDK startup
performance" was retired in v4.0 because the trade-offs (hooks skipped,
API-only auth that breaks Claude Max OAuth, missing CLAUDE.md/rules
auto-load) outweighed the startup gain. The --dangerously-skip-permissions
flag alone gives the same non-interactive behavior with all guarantees
preserved.
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 · 137 lines · 79 tokens per session scan A 39b4240f2dda
full-sprint is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,475 once invoked, about $0.0004 per session on Opus 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
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.