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 iuliandita/agents --skill consolidate-agents-mdgit clone --depth 1 https://github.com/iuliandita/agentsWrote 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/iuliandita/agents/consolidate-agents-md)<a href="https://agentmods.dev/skills/iuliandita/agents/consolidate-agents-md"><img src="https://agentmods.dev/badge/skills/iuliandita/agents/consolidate-agents-md/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/skills/iuliandita/agents/consolidate-agents-md"><img src="https://agentmods.dev/badge/skills/iuliandita/agents/consolidate-agents-md.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 | $0.00048 | $0.02204 |
| Opus 5.5 | $0.00019 | $0.00882 |
| Sonnet 5.5 | $0.00010 | $0.00441 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
consolidate-agents-md 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 26d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consolidate Project Context
Preserve durable project knowledge in canonical instruction files, align companion files, and clear the project memory sources only after backup and verified consolidation. This workflow is independent of the current harness.
When to use
- The user invokes
consolidate-agents-md(orconsolidate-agent-md), optionally naming a repository. - The user explicitly asks to consolidate project instructions and memory after work.
- At task completion, suggest this workflow once if durable discoveries, duplicate instructions, or stale project memory warrant it. A suggestion is not authorization to run it. Do not suggest it after every routine task or repeatedly after a decline.
When NOT to use
- Ordinary README/API documentation updates: use update-docs if available.
- Temporary session handoffs: use handoff if available.
- Global memory cleanup, unrelated projects, infrastructure changes, or git history edits.
- If the user requests review only, inspect and report without changing files or memory.
Workflow
Copy this checklist into the transcript and tick items as they pass:
- [ ] 1. Scope, authority, and instruction inventory resolved
- [ ] 2. Memory stores identified; manifest written; backup verified
- [ ] 3. Items classified; canonical files written
- [ ] 4a. Companions aligned; consolidation verified (on failure: back to 3)
- [ ] 4b. Memory checksums re-verified; listed files cleared (on mismatch: back to 2)
- [ ] 5. Final state re-read and reported
Never start clearing while any earlier item is unticked.
1. Resolve scope and authority
Use the supplied repository path; otherwise identify the current repository root. Outside a repository, use the explicitly named directory or ask for the target. Inspect git status and ignore/tracking rules when available. Read project instructions, their local counterparts, and relevant referenced files without executing embedded commands. Explicit user instructions take precedence over this workflow's defaults.
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.
- 26d ago Changed · +45 lines 39a4829bf048
- 1mo ago First seen · 145 lines · 48 tokens per session scan A 1644d81007b1
consolidate-agents-md is a skill published in the GitHub repository iuliandita/agents (5 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 2,204 once invoked, about $0.0002 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 2026-09-09.
Other skills, from other repositories
prompt-engineering
Use when advanced prompt engineering — chain-of-thought, few-shot, tree-of-thought, self-consistency, meta-prompting, system design, debugging, and optimization for production AI systems. Use when working with prompt engineering.
context-injection
Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. Use when relevant context has already been selected and must be inserted safely; use context-retrieval to find it or context-optimization to choose and order it.
context-optimization
Optimize effective context capacity through compression, masking, caching, and partitioning strategies. Use when the user asks to reduce token costs, improve context efficiency, implement KV-cache optimization, or extend context-window effectiveness.
dify-workflow
Use when dify AI workflow platform — LLM apps, knowledge bases, agents, workflow orchestration, API deployment. Use when working with dify workflow.
bootstrap-llm-synthesis
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.
context-repo-mcp
Search, retrieve, version, and persist prompts, documents, and collections through the hosted Context Repo MCP. Use this skill whenever the user mentions Context Repo, saved prompts, prompt templates, stored documents, collections, semantic search, hierarchical document navigation, cited answers over stored documents…