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 skills add fjpulidop/specrails-core --skill retrygit clone --depth 1 https://github.com/fjpulidop/specrails-coreWrote 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/fjpulidop/specrails-core/retry)<a href="https://agentmods.dev/skills/fjpulidop/specrails-core/retry"><img src="https://agentmods.dev/badge/skills/fjpulidop/specrails-core/retry.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 | $0.00021 | $0.00630 |
| Opus 5 | $0.00010 | $0.00315 |
| Sonnet 5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
retry 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 today.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retry an Implementation Pipeline
Plugin invocation mapping: logical sr-architect/sr-developer/sr-reviewer IDs use the installed plugin agents specrails:architect, specrails:developer and specrails:reviewer. Profile IDs remain logical; verify available plugin agents instead of requiring local agent files.
Input: $ARGUMENTS — existing change and optional --from .
Resolve the exact run
Use the same absolute SPECRAILS_PIPELINE_RUNTIME and SPECRAILS_EXECUTION_CONTEXT. The managed fallback is .specrails/runtime/pipeline.mjs; the standalone workspace pointer is only discovery. Do not initialize another run, choose the newest change, replace frozen tickets from mutable backlog, or trust old ad-hoc pipeline state.
node "${SPECRAILS_PIPELINE_RUNTIME:-.specrails/runtime/pipeline.mjs}" status --json
Verify runId/change match. Preserve context.specs, selected roots, backlog identity and ownership. The artifact compatibility root is ${SPECRAILS_REPO_DIR:-.}, not necessarily the framework workspace.
Resume earliest invalid evidence
Follow resumePhase and receipt reasons. Completed valid phases require no model call. Blocked/failed is resumable; never convert dependent implementation into skipped. Explicit --from can reopen an earlier phase, but runtime prerequisite checks still apply.
node "${SPECRAILS_PIPELINE_RUNTIME:-.specrails/runtime/pipeline.mjs}" phase --phase <phase> --status running
| Phase | Resume action |
|---|---|
| architect | Repair official design artifacts/confidence; unblock development only after actual gate passes. |
| developer | Continue unchecked tasks, retain completed code; scoped repairs followed by one full receipt. |
| reviewer | Review acceptance/confidence; reuse current full evidence, refresh after edits. Do not redo valid architecture because review was blocked. |
| archive | Fresh archive-check, then authorized official archive/sync only; preserve approved confidence bytes. |
| ship | Only Core-owned and authorized; resume missing repository delivery without duplicating successful commits/PRs. |
| ci | Check existing delivery; never reship merely because CI needs retry. |
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.
- today Changed · -322 lines f2140e0b7361
- 8d ago First seen · 373 lines · 21 tokens per session scan A eca4f1b9c184
retry is a skill published in the GitHub repository fjpulidop/specrails-core (9 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 630 once invoked, about $0.0001 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
local-execution-planner
Plan a repository task for execution by a small local coding model, then hand the plan to the local executor over MCP. Inspect the codebase, decompose the work into self-contained sequential prompts, define deterministic eval gates, validate the manifest, and submit it for execution. Never implement the task.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…