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 agentmods add commands/adilkalam/orca/continuegit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00015 | $0.01129 |
| Opus 5 | $0.00008 | $0.00564 |
| Sonnet 5 | $0.00003 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
continue 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 yesterday.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/continue - Session Resume Info
PURPOSE: Show recent recording sessions (telemetry) and route you to the right resume path. Recording sess-... ids are internal to orca-record; they are NOT Claude Code conversation ids, so they are shown for context only and must never be passed to --continue/--resume.
EXPECTED OUTCOME: A list of recent sessions plus the correct way to resume -- /session-resume when active-task.md is fresh, otherwise native claude --continue.
Step 1: Check Recording Layer Status
Verify recording database exists:
if [ ! -f .orca/recording.db ]; then
echo "No recording database found at .orca/recording.db"
echo "Recording layer may not be active in this project."
exit 0
fi
Verify sqlite3 available:
if ! command -v sqlite3 >/dev/null 2>&1; then
echo "sqlite3 not found. Required for session queries."
exit 0
fi
Step 2: Parse Arguments
Arguments:
- (none): List recent sessions
- : Show specific session's continue command
Examples:
/continue # List recent sessions
/continue sess-19c6983c46029c7 # Specific session info
Step 3: Query Recent Sessions
Query the recording database:
sqlite3 .orca/recording.db "
SELECT
s.id,
s.started_at,
s.ended_at,
s.state,
s.step_count,
json_array_length(COALESCE(s.files_touched_json, '[]')) as files_touched
FROM sessions s
ORDER BY s.started_at DESC
LIMIT 5;
"
Step 4: Format Output for User
Display session list with continue commands:
Recent sessions (recording telemetry):
[1] sess-19c6983c46029c7 today, 14:30 -- 5 steps, 12 files, state: ended
[2] sess-abc123def456 yesterday -- 12 steps, 28 files, state: ended
[3] sess-def789ghi012 2 days ago -- 8 steps, 15 files, state: ended
To RESUME where you left off:
- If you saved intent this session: run /session-resume (reads .orca/orchestration/active-task.md)
- Otherwise: run `claude --continue` (native; reloads the most recent conversation -- takes NO id argument)
(The sess-... ids are orca-record internal identifiers for telemetry, not Claude conversation ids.)
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.
- yesterday First seen · 163 lines · 15 tokens per session scan A 3e4ce4b098d4
continue is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,129 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.