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/bleak-ai/gcontextWrote 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/bleak-ai/gcontext/add-to-context)<a href="https://agentmods.dev/commands/bleak-ai/gcontext/add-to-context"><img src="https://agentmods.dev/badge/commands/bleak-ai/gcontext/add-to-context.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 | $0.00016 | $0.00460 |
| Opus 5 | $0.00008 | $0.00230 |
| Sonnet 5 | $0.00003 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
add-to-context 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.
What it actually says
Review journal files and session transcripts. Propose changes before you write to context/project/.
-
Run
uv run context/system/scripts/journal-review.py --list. Keep its JSON output. Set the review cutoff to the current ISO timestamp. Read every journal path in thejournallist. -
Skip the transcript of the current session (the hook already captured it). For each other path in the
transcriptslist, runuv run context/system/scripts/journal-review.py --condense <path>. Write each command output to a separate temporary text file under the scratch directory that the harness gives you. Use the OS temp directory when the harness gives no scratch directory. Read every condensed text file. -
Collect all durable facts. Include decisions, paths, names, measured numbers, results, traps, and closed paths. Drop duplicates across sessions. Drop narration and transient chatter.
-
Read context/project/index.md and all relevant project files. For each fact, decide PRESENT, STALE, or MISSING. Use the Save routing in context/system/rules.md. PRESENT means no change. STALE replaces the wrong fact. MISSING adds the fact.
-
Propose one line per STALE or MISSING fact. Give its target path. Include each new file or folder that the file test and folder test require. Do not write yet.
-
Stop and wait for the exact reply
apply. Treat any other reply as a rejection. Use its comments in a new proposal. -
On
apply, write the approved facts. Runuv run context/system/scripts/sync-index-files.py --write. Then runuv run context/system/scripts/sync-index-files.py --check. Fix all reported problems. -
Count the unique session file names in the review input. Append this line to context/system/log.md with the review cutoff:
- YYYY-MM-DD: journal review, N sessions, up to <iso> -
Report one line per file changed. Never commit.
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 First seen · 39 lines · 16 tokens per session scan A 483c73aaf7dd
add-to-context is a command published in the GitHub repository bleak-ai/gcontext (24 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 460 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 2026-09-07.
Other commands, from other repositories
remember
Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
compact-prep
Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.
revise-claude-md
Update CLAUDE.md with learnings from this session.
drift-detect
Configuration drift detection command. Finds inconsistencies, orphaned components, and stale content in the Badi system.
wrap-up
End-of-day ritual command. Prepares the day for closure and sets the stage for tomorrow.