Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add WangChangxin0809/repo-agent-harness/plugin install repo-agent-harnessWrote 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/wangchangxin0809/repo-agent-harness/consolidating-notes)<a href="https://agentmods.dev/skills/wangchangxin0809/repo-agent-harness/consolidating-notes"><img src="https://agentmods.dev/badge/skills/wangchangxin0809/repo-agent-harness/consolidating-notes/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/wangchangxin0809/repo-agent-harness/consolidating-notes"><img src="https://agentmods.dev/badge/skills/wangchangxin0809/repo-agent-harness/consolidating-notes.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 | $0.00126 | $0.01425 |
| Opus 5 | $0.00063 | $0.00713 |
| Sonnet 5 | $0.00025 | $0.00285 |
| Haiku 4.5 | $0.00013 | $0.00143 |
Grade A, and why
consolidating-notes 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consolidation
Governs: shared/scripts/consolidate.py
Notes accumulate faster than they are corrected. After a few months a pile contains contradictions, entries about flags that were removed, and — buried in it — the measurements that are the only reason any of it is worth keeping.
The mechanism that fixes this is a synthesis pass over a frozen input, producing a separate output you compare before adopting. Claude's Dreams API implements exactly this shape and never mutates its input; the same shape works by hand, and is what the scripts here do.
The invariant
Never synthesize in place. The input is frozen, the output is new, and adoption is a decision you make after reading a diff. In-place editing destroys the evidence needed to tell a good merge from a lossy one, and lossy merges are the normal failure — they read beautifully.
python3 ${CLAUDE_PLUGIN_ROOT}/shared/scripts/consolidate.py prepare --notes .agent-notes --sessions .agent-sessions
# snapshot is chmod'd read-only; the synthesis writes to .consolidation/candidate/ only
python3 ${CLAUDE_PLUGIN_ROOT}/shared/scripts/consolidate.py diff
diff reports three things, in the order they matter:
- What is gone. Every measurement, commit hash, and path present in the input and absent from the candidate, quoted. This is the check the whole invariant exists to enable, and it is mechanical — do not do it by eye.
- What has no destination. Entries that survived without a
ROUTE:line. A consolidation whose output is a tidier pile of notes has moved nothing. - Unchanged / rewritten / dropped / new, by name.
Read 1 and 2. Skim 3.
What must survive verbatim
Two things, and they are the two most likely to be smoothed away because they read as noise:
Measurements and identifiers. 87ms, 3.6s, 9de1104, a file path, a
version. Paraphrasing a number destroys it — "noticeably slower" cannot be
compared against a later reading, and a rounded commit hash cannot be checked
out. Every reading carries the commit it was taken on, or it expires silently.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 127 lines · 126 tokens per session scan A 0aba714f027e
consolidating-notes is a skill published in the GitHub repository WangChangxin0809/repo-agent-harness (2 stars, last pushed 11d ago), licensed MIT. It adds 126 tokens to every session and 1,425 once invoked, about $0.0006 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
apply
Use when a staged proposal has been reviewed and signed off — REVIEW.md Step 3 ticked reviewed or provisional — and is ready to promote into the live contextualizer.
vault-update
Incrementally update an existing vault — detect code changes via git diff and static file changes via SHA256, then re-analyze and rewrite only affected pages.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…