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.
git clone --depth 1 https://github.com/Mozurok/fhorja.devWrote 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/mozurok/fhorja.dev/pr-package)<a href="https://agentmods.dev/commands/mozurok/fhorja.dev/pr-package"><img src="https://agentmods.dev/badge/commands/mozurok/fhorja.dev/pr-package/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/commands/mozurok/fhorja.dev/pr-package"><img src="https://agentmods.dev/badge/commands/mozurok/fhorja.dev/pr-package.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00109 | $0.06548 |
| Opus 5.5 | $0.00044 | $0.02619 |
| Sonnet 5.5 | $0.00022 | $0.01310 |
| Haiku 4.5 | $0.00011 | $0.00655 |
Grade A, and why
pr-package 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 13d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-package
Act as a senior engineer preparing a full delivery package for the active engineering task based on the real git diff.
Goal: Prepare a clean delivery package for GitHub using the actual implementation changes in the current branch compared against an explicit integration base branch, then persist the result in the task repository.
Mandatory context bootstrap (before any output):
- Read these sections in
WORKFLOW_OPERATING_SYSTEM.mdfirst:## LLM execution contract## Editor mode policy(mode definitions only; the tool mapping table is lazy-loaded inwos/editor-mode-mappings.mdand needed only for non-Claude-Code tools)## Global output contract(including Adaptive handoff and Mode selection rule)## Cross-cutting workflow guardrails
- Bootstrap tiers: the light-weight commands (
branch-commit,what-next,where-we-at,slice-closure,compact-task-memory) plus the high-frequencyimplement-approved-sliceandsync-task-state(v3 wave1 item D) read the four sections above with two subsections of## Cross-cutting workflow guardrailsskipped:### External web access (centralized)and### Sequencing heuristics (by phase). Everything else is read at every tier, including### Proposal vs approved persistenceand### Substrate peer ownership (per ADR-0034), since all seven write substrate sections and reason about PROPOSED (state-reconcilestays on the full tier for cross-artifact judgment). The full tier is measured at 12109 tokens, the four always-read sections combined; the two skipped subsections are 1,034 of those (measured 2026-09-28), so the reduced tier is about 11,074. The leaf-reviewer tier (verify-against-rubric, ADR-0226) reads only## Global output contract, measured at 5215 tokens, plus its rubric. - Session bootstrap reuse (skip-if-unchanged; v3 wave1 item D): WHEN this conversation already read the bootstrap sections in an earlier turn still VISIBLE in the context window AND
WORKFLOW_OPERATING_SYSTEM.mdhas not changed since, the command MAY skip the re-read and cite the earlier one, emitting one Command transcript line:Bootstrap: reusing turn <N> read, WOS unchanged. Scoped exception to the context-budget re-fetch rule (wos/context-budget.md, "The re-fetch rule"), because these sections are one large, static, byte-identical read repeated every turn; every other tool result still re-fetches. VISIBLE means the section text itself is still present and quotable now, not merely that a record of the earlier read exists: a harness that clears a tool result while the record survives (ADR-0114) has not satisfied VISIBLE, and self-declared memory after a compaction never qualifies. A stateless-per-turn harness is excluded. The transcript line is mandatory; a silent skip is invalid output. - Resolving the spec and
wos/<topic>.md: canonical repository FIRST. Otherwise use active-adapter docs:~/.claude/workflow-docs(CLAUDE_WORKFLOW_DOCS_DIR),~/.cursor/workflow-docs(WORKFLOW_DOCS_DIR; project.cursor/workflow-docson project installs),~/.codex/workflow-docs(CODEX_WORKFLOW_DOCS_DIR), or<kimi-home>/workflow-docs(KIMI_WORKFLOW_DOCS_DIR). Nonempty overrides win. Kimi home:KIMI_CODE_HOME, else existing~/.kimi-code, else existing~/.kimi, default~/.kimi-code. Use one root for both paths; try other adapters if absent or unknown. Report resolved root, fallback to other adapters, or missing mandatory context in### Command transcript. Installed snapshots refresh and prune retired topics only on sync. - Read additional sections only when relevant to this command's role.
- Align all routing recommendations and next-command suggestions with the current command set.
- Official next-command names only: recommendations, including
Run now, use registered names fromcommands/<name>.mdorcommands/<name>/SKILL.md; installed mode uses the available Fhorja command or skill inventory. No invented aliases.Run now: nonewithMode: N/Aends only if no honest next step exists, defined under### Official command names (routing integrity)(ADR-0126). Required inputs: - active task folder path
- TASK_STATE.md
- DECISIONS.md
- IMPLEMENTATION_PLAN.md
- target repo (only for multi-repo tasks where
SOURCE_OF_TRUTH.mdhas a## Repositoriessection): the repo identifier this invocation packages. Must match one entry in the## Repositoriessection. Multi-repo tasks invokepr-packageonce per repo, with one invocation producing one repo's PR. See the spec## Multi-repo support (v1)for the schema. - explicit git base branch to compare against (example:
origin/main,origin/staging, or a named remote branch). WHEN an attended chain on a task branch reached this command frombranch-commit --applyand no base was given, use theBase branch:line inTASK_STATE.md ## Resume notes(the branch the task branch was cut from), else the base recorded inSOURCE_OF_TRUTH.md(orTASK_PREFERENCES.md), elseorigin/HEAD, and cite which one supplied it instead of asking (ADR-0233). For multi-repo tasks, this is the base branch for thetarget repo(which may differ across repos and is recorded per-repo in## Repositories). - current local branch name (as shown by
git branch --show-current) - working tree context (as shown by
git status --porcelainor an explicit statement that the working tree is clean) - explicit diff commands used (at minimum):
git fetch <remote> <base>(run first; the diff is taken against the freshly fetched ref, never a stale local one)git diff <base>...HEAD- optional:
git diff --stat <base>...HEAD git status --porcelainplusgit diffandgit diff --stagedWHEN the committed diff is empty. Uncommitted work in the working tree is still the change under delivery: package it and say plainly that it is uncommitted, so the branch-and-commit steps come before the push step. An empty<base>...HEADis NOT proof there is nothing to deliver, and reporting a healthy package over an empty diff is the silent-empty-scope failure this line exists to prevent.
- real git diff vs the explicit base branch, or the working-tree diff when the branch carries no commits yet
- latest validation/test evidence if available
- last completed step from TASK_STATE.md (command + summary)
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.
- 13d ago Changed · -54 tokens per session 93a9ded7fc1f
- 16d ago Changed · -1 lines eeb4bf13ba13
- 23d ago Changed · -1 lines fd04e3eab852
- 24d ago Changed · +14 lines · -53 tokens per session bd6012cdfb74
- 1mo ago First seen · 157 lines · 216 tokens per session scan A 86de056ca170
pr-package is a command published in the GitHub repository Mozurok/fhorja.dev (10 stars, last pushed 13d ago), licensed MIT. It adds 109 tokens to every session and 6,548 once invoked, about $0.0004 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 2026-09-03.
Other commands, from other repositories
pr-reviewer
Review a Git branch as a PR against the base branch (auto-resolved — main/master) judged by THIS repo's contract (CLAUDE.md + .claude/skills/). Three-dot diff, route changed paths to skills, verify (eslint/prettier/tsc + tests), tiered report + confidence. Optional gated fix + commit after the report.
ijfw-ship
Run the IJFW workflow Ship phase (Deep D6). Pre-flight, deploy, and close. Usage: /ijfw-ship.
prp-commit
Quick commit with natural language file targeting: describe what to commit in plain English.
codex-review
Run OpenAI Codex code review on current changes or a specific branch/commit.
changelog-auto
Auto-generar entradas de CHANGELOG.md desde commits convencionales. Usa cuando el usuario dice "generar changelog", "update changelog", "changelog", "conventional commits", "auto changelog", "release notes", "generar release notes", "伽 changelog". Genera entradas desde conventional commits (feat, fix, docs, etc.) con…
guardian
Revisión de código IA como pre-commit hook — Guardian Angel.