Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bnet47/codexiconnpx agentmods add skills/bnet47/codexicon/context-dumpWrote 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/bnet47/codexicon/context-dump)<a href="https://agentmods.dev/skills/bnet47/codexicon/context-dump"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/context-dump/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/bnet47/codexicon/context-dump"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/context-dump.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 | $0.00026 | $0.00593 |
| Opus 5.5 | $0.00010 | $0.00237 |
| Sonnet 5.5 | $0.00005 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
context-dump 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context checkpoint
Create or resume a concise checkpoint without transcript archaeology. Semantic checkpoints are explicit project writes; hooks never create or commit them automatically.
1. Choose the branch
- For a checkpoint or handoff request, continue with Create.
- For a resume or continuation request, continue with Resume.
2. Create
Inspect the active request/spec/plan, declared changed files, latest verification, and blockers. Do not copy secrets, large logs, transcript content, or code that already exists in project files.
Run the repository manager from the root:
python scripts/codexicon.py checkpoint --slug [short-slug] --title "[short title]" --summary "[working, partial, and broken state]" --resume-note "[minimum critical continuation context]" --next "[immediate concrete action]" --related [relative spec or plan path] --verification "[exact command — result and time]" --blocker "[blocker and required input]" --decision "[decision and rationale]"
Repeat --next, --related, --verification, --blocker, and --decision as needed. Omit optional categories that are empty. Quote values for the active shell; never interpolate command output or untrusted text into the command.
Use --changed [relative-path] for each source or document path changed in the current task. These are explicit evidence names, not a request to inspect Git status.
The manager validates related and explicitly supplied changed paths, captures local contract/task/path identities without invoking Git, and atomically writes agent_docs/sessions/[YYYY-MM-DD]-[slug].md. It refuses an existing filename. Do not hand-edit the first metadata line.
3. Resume
Run:
python scripts/codexicon.py resume
python scripts/codexicon.py doctor
Use the newest path-compatible checkpoint as orientation, then verify its local contract/task/path identities, related paths, changed-path evidence, and verification claims before acting. A checkpoint is evidence, not authority to discard later user changes or repeat external side effects. Git branch, index, and history checks belong only to $ship.
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.
- 1mo ago Changed · +2 lines 9ff1c215cad4
- 1mo ago First seen · 47 lines · 26 tokens per session scan A a7068db95734
context-dump is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 20d ago), licensed MIT. It adds 26 tokens to every session and 593 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
context-engineering
Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing what loads at boot versus on demand, sizing an install or an always-loaded file, fixing an agent that drifts, repeats itself, or forgets constraints mid-task, planning compaction or summarization…
claude-compaction-restore
Use when a Claude Code session is about to compact, has just compacted, reached its context limit, resumed after /compact, or must rebuild its working picture of a long-running seat from its own restore map, its JSONL transcript and the files it touched.
retiring-and-inheriting-a-seat
Use when you are a sitting agent near your context threshold (85%) and a PLANNED seat transition is due — retire deliberately and hand your seat to a fresh successor primed from a packet, rather than let compaction degrade you. Covers the handover packet, the append-only lineage ledger (one row per tenure)…
llm-wiki
Build and maintain a persistent, interlinked Markdown knowledge base: ingest sources once, cross-reference and flag contradictions, answer questions from it, and check it for broken links and gaps.
session-compaction-and-restore
Use when reasoning about what survives compaction/context-loss/restart/seat-refresh, designing a high-fidelity restore packet, or distinguishing native runtime resume vs fork vs artifact-backed mental-model rebuild. Covers the 4 failure modes that prevent honest restore (compacted seat drops hot potato; restore packet…
notebook-gardening
Keep the agent's notebook true: find duplicates and contradictions, correct beliefs in place with their source, fade stale ones, and list for the Commander what to delete.