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/jonase47/ccpr/p8-iterationgit clone --depth 1 https://github.com/jonase47/ccprWrote 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/jonase47/ccpr/p8-iteration)<a href="https://agentmods.dev/commands/jonase47/ccpr/p8-iteration"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p8-iteration.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 5.1 | $0.00000 | $0.02151 |
| Opus 5 | $0.00000 | $0.01076 |
| Sonnet 5 | $0.00000 | $0.00430 |
| Haiku 4.5 | $0.00000 | $0.00215 |
Grade A, and why
p8-iteration 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 2d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p8-iteration – Evaluate Feedback, Maintain Backlog & Plan Next Sprint
Evaluates user feedback and operational insights, maintains the backlog, and initiates the next iteration. This is the link between ongoing operations and the next development round – the engine of the evolution loop.
Argument: $ARGUMENTS = [Topic/feature area, e.g. "user feedback week 10", "technical debt", "new feature ideas"]
If provided: Focus the iteration planning on the specified topic. If not provided: Read all available inputs (KPI reports, incident reports, user feedback) and conduct complete iteration planning. If any context is missing, ask about the available feedback sources.
0. Work-item adoption guard (ADR-0002 §8)
Run python3 ~/.claude/scripts/workitems.py list.
- Non-empty array → the project uses the structured store. Use the CLI for the backlog updates in step 2B below (instead of hand-editing BACKLOG.md prose).
[]and nodocs/workitems/directory → still on prose. Edit BACKLOG.md directly, as before. Emit one line: "Tip: runliftto adopt the structured work-item store."[]butdocs/workitems/exists → adopted store, just empty right now. Treat as adopted: use the CLI, not the prose fallback.
See Manual/WORKITEMS.md §8 for the full guard rationale and the status-verb mapping.
Execution
1. Read Context
Read the following files (if available):
- KPI_REPORT_[current].md (business insights and recommendations)
- INCIDENT_REPORT_*.md / OPS_REVIEW_*.md (technical operational insights)
- SECURITY_UPDATE_*.md (open security findings)
- BACKLOG.md (current backlog status) /
workitems list(structured store, per the §8 guard) - PROJECT_PLAN.md (milestones and progress to date)
- FEATURES.md (original prioritisation as reference)
2. Delegation to Project Planner Agent (Lead)
Delegate iteration planning to the project-planner agent:
Plan the next iteration based on: $ARGUMENTS Input: [Apply KPI recommendations, incident findings, security updates, user feedback]
A. Feedback Evaluation Collect and categorise all inputs from the ongoing operational phase:
Source Feedback/Finding Category Priority KPI report (e.g. churn at feature X) Feature adjustment High Incident report (e.g. recurring DB timeout) Technical debt Medium Security update (e.g. open CVE) Security Critical User feedback (e.g. request for export function) New feature Low Categories: Bug fix / Feature adjustment / New feature / Technical debt / Security / Performance / UX improvement
B. Update Backlog Using the guard result from step 0:
- Structured store: new items from the feedback evaluation →
workitems create --title "<item>" --type feat --description "<estimate + acceptance criteria>"(check the full, unfilteredworkitems listfor a matching title first — trim + casefold — so a re-run never duplicates an already-added item; record the assigned**Work-Item:** WI-NNNNid in the generated view, §4). Outdated items (no longer relevant) →workitems set-status <id> "Cancelled"(resolve<id>by matching title againstworkitems list), never a silent removal — a Cancelled item stays traceable. Re-prioritising existing items (ranking, not a status change) has no CLI equivalent yet — keep that ordering in the generated BACKLOG.md view.- Prose fallback: add new items to BACKLOG.md (with estimates and acceptance criteria); re-prioritise existing items; mark or remove outdated items (no longer relevant).
- Make technical debt visible as its own epic (if accumulated) — either way, this is a BACKLOG.md view-level grouping, not a per-item CLI operation.
C. Evolution Loop Decision Based on the scope and nature of the next work: where does the evolution loop go?
If... Then back to... New features with significant scope P1 (Conception) – plan new user journeys, features Architecture must be adjusted for scaling or new features P3 (Architecture) – write ADR, adjust model Small improvements and bug fixes P5 (Implementation) – directly into sprint Clearly recommend which loop entry point you recommend for the next iteration and why.
D. Prepare Next Sprint (if P5 loop) If the next iteration goes directly into implementation:
- Propose a sprint goal
- Select the top stories from the updated backlog
- Hand over to
/p4-sprintfor formal sprint planning
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.
- 2d ago First seen · 162 lines · 0 tokens per session scan A 782c90f0c3e5
p8-iteration is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,151 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 2026-09-03.
Other commands, from other repositories
sdd-implement
Execute a task list in dependency order, tests before implementation for each task, halting on any non-parallel failure instead of pressing ahead.
wiki-tune
Tune wiki schema and conventions interactively.
experiment
Design A/B test with statistical rigor. Usage: /mindforge:experiment [feature] [--metric conversion|engagement|revenue] [--duration 2w].
pseo-init
Use when: kullanıcı "yeni proje", "init", "proje kur", "yeni domain ekle", "scaffold" gibi ifadeler kullanır ya da /pseo-init çağırırsa. Also use when: portföye yeni bir SEO projesi alındı, projects/{slug}/ klasörü ve project.config.json dosyasının schemaya uygun ilk hâli üretilecek; brief'te slug + domain + market…
forge-insights
Analyze past sessions for error patterns, file activity, and recommendations.
forge-context-status
Report on current context window usage, cache health, and compaction recommendation. Read-only — does not compact.