| name | lisa-linear-access |
| description | Vendor-neutral access layer for Linear. Linear skills MUST delegate through this skill rather than calling Linear MCP tools or Linear GraphQL directly. Per the credential-substrate-precedence contract, resolves LINEAR_API_KEY + Linear GraphQL first — ahead of the Linear MCP — whenever the key is present and identity-matches the configured workspace/team, and falls back to the Linear MCP when the token path is unavailable. Identity-match is mandatory on both substrates. |
| allowed-tools | ["Bash","Read","Skill"] |
Linear Access: $ARGUMENTS
Single chokepoint for Linear operations. Caller skills (linear-*) MUST go
through this skill. They MUST NOT call mcp__linear-server__* tools directly or
curl https://api.linear.app/graphql themselves.
Invocation Contract
operation: list-teams [query:<KEY>]
operation: get-team id:<ID>
operation: list-projects [team:<KEY>] [label:<NAME>] [state:<arr>]
operation: get-project id:<ID>
operation: save-project payload:{...}
operation: list-issues [team:<ID>] [project:<ID>] [label:<NAME>] [state:<NAME>] [state_type:<arr>]
operation: get-issue id:<ID>
operation: save-issue payload:{...}
operation: list-workflow-states team:<ID>
operation: create-workflow-state payload:{...}
operation: list-comments issue_id:<ID>
operation: save-comment issue_id:<ID> body:"..."
operation: history id:<ID>
operation: list-issue-labels [team:<ID>]
operation: create-issue-label payload:{...}
operation: list-project-labels
operation: create-project-label payload:{...}
operation: list-documents project_id:<ID>
operation: get-document id:<ID>
Return parsed JSON in a <result> block. On failure, prefix the message with
Error: and include the failing operation name.
Substrate Selection
Read config:
WORKSPACE=$(jq -r '.linear.workspace // empty' .lisa.config.json 2>/dev/null)
TEAM_KEY=$(jq -r '.linear.teamKey // empty' .lisa.config.json 2>/dev/null)
Probe in order — the ordering is the shared credential-substrate-precedence
contract, not a Linear-local choice. The first tier that is ready and
identity-matches wins; a substrate authenticated against a different
workspace/team is skipped, never used, at either tier.
- Tier 1 — configured-provider substrate:
LINEAR_API_KEY with Linear GraphQL
(https://api.linear.app/graphql), resolved through lisa-secrets-access.
Identity-match by querying viewer { organization { urlKey } } (plus
teams when linear.teamKey is configured) and comparing to
.lisa.config.json. A key that resolves to a different organization fails the
gate — warn, skip the tier, and continue down the ladder.
- Tier 2 — interactive MCP fallback: Linear MCP, if
mcp__linear-server__list_teams is available and can list the configured
workspace/team (that listing is the identity match). Used when tier 1 is
genuinely unavailable: no LINEAR_API_KEY, no GraphQL adapter for the
operation, or a Linear API outage.
The Linear GraphQL docs support personal API keys for scripts and authenticate
with an Authorization: <API_KEY> header, so the token tier works identically on
a developer laptop, in CI, in a cloud routine, and in a subagent — which is why it
leads. If neither tier works, fail with:
Error: no Linear access substrate available. Authenticate the Linear MCP or set LINEAR_API_KEY.
GraphQL Adapter
All GraphQL calls use:
read_linear_key() {
[ -n "${LINEAR_API_KEY:-}" ] && { echo "$LINEAR_API_KEY"; return; }
local candidates=()
if [ -n "${CLAUDE_PLUGIN_ROOT:-}" ]; then
candidates+=("$CLAUDE_PLUGIN_ROOT/skills/lisa-secrets-access/scripts/resolve-secret.mjs")
fi
if [ -n "${PLUGIN_ROOT:-}" ];
candidates+=()
candidates+=(node_modules/@codyswann/lisa/plugins/lisa/skills/lisa-secrets-access/scripts/resolve-secret.mjs)
resolver
tried=()
resolver ;
tried+=()
[ -f ];
via_lisa
via_lisa=$(node get LINEAR_API_KEY 2>/dev/null) \
&& [ -n ] && { ; ; }
>&2
>&2
>&2
1
}
() {
query=
variables=
key
key=$(read_linear_key) || {
>&2
>&2
1
}
jq -n --arg query --argjson variables \
|
curl -sS -X POST \
-H \
-H \
--data-binary @-
}
Map operation names to Linear GraphQL queries/mutations in this access skill.
Consumers pass business-shaped arguments only; they do not embed GraphQL.
list-workflow-states — the team's states, and which one it creates into
list-workflow-states team:<ID> returns one node per state with id, name,
type, position, and isTeamDefault.
isTeamDefault is true for the single state named by the team's
defaultIssueState — where Linear puts every brand-new Issue. Callers need it to
enforce the rule that linear.workflow.ready must be a lane a human moves an
Issue into: pointing ready at the default inverts the gate, so the
claimable lane means "nobody has touched this" rather than "a human marked this
ready", and build-intake dispatches unapproved work. /lisa:setup:linear refuses
to resolve ready onto it, and /lisa:validate-tracker-mapping classifies a
config that already does as INVERTED.
It belongs on this operation rather than in a separate get-team call because
every caller that needs it is already enumerating states, and a second round trip
is a second chance for the two answers to disagree. A team with no
defaultIssueState set yields isTeamDefault: false on every node — report that
honestly; do not fall back to guessing by name or position.
query($teamId:String!){
team(id:$teamId){
defaultIssueState{ id }
states(first:100){ nodes{ id name type position } }
}
}
Set isTeamDefault per node by comparing node.id against
team.defaultIssueState.id. On the MCP substrate, which exposes states without
the team's default, resolve the default through the team record and join on id
the same way.
history — transition history (read-only)
history id:<ID> returns an Issue's ordered past state changes — the raw
material for rejection detection (an Issue that reached a review/done-ward
state and is now back in ready). IssueHistory is reachable today through the
existing linear_graphql adapter but was not in the documented contract; an
undocumented-but-reachable capability is not exposed, so it now appears in the
Invocation Contract above. Reuse the existing adapter — this is a
contract/surface change, not a new transport (the integration-access-layer
rule forbids consumers from reaching around the layer).
Query through linear_graphql (oldest→newest; page history(first:…, after:…)
via pageInfo for busy Issues so history never silently truncates):
query($id:String!){
issue(id:$id){
history(first:100){
pageInfo{hasNextPage endCursor}
nodes{
createdAt
fromState{name type}
toState{name type}
actor{name}
addedLabelIds
removedLabelIds
}
}
}
}
- Shape. For each node emit
{ from, to, when, who } — fromState.name →
toState.name, createdAt (ISO timestamp), actor.name. Nodes with no
fromState/toState are non-state edits (label-only, assignee, etc.); keep
them for the label stream, skip them for workflow-state ordering.
- Build lanes are STATE-driven, so the
from/to stream above is the primary
signal. lisa-linear-build-intake keys the queue on workflow states
(linear.workflow), and IssueHistory inlines fromState.name /
toState.name directly — no catalog cross-reference, no ID resolution, no
reconstruction. Callers needing lifecycle transitions read them straight off
the node. This is strictly better than the label stream below and is why the
Linear adapter moved to states.
- Label history (honest caveat, still needed for MARKERS and the PRD lane).
human_needed is a label, and the PRD lifecycle rides on project labels, so
label moves still matter for those. IssueHistory carries label changes as
addedLabelIds / removedLabelIds — arrays of label IDs, not names. It
does not inline label names, and it does not carry the label's full
prior/next set — only the per-event deltas. Resolve IDs → names by
cross-referencing list-issue-labels. Do not overclaim: a caller that needs
label transitions reconstructs them from the ID deltas plus the label catalog,
not from an inline name on the history node. A caller reading a build
lifecycle transition should not be in this bullet at all — use the state
stream.
- Empty is valid. An Issue that never changed state returns an empty
history — an empty history is a valid result, not an error.
- Graceful degrade — never block the build. A failed history fetch returns
the layer's
Error: result. Callers MUST treat that as unknown history
and proceed — a history read failure never blocks the build. MCP cannot reach
IssueHistory, so the history operation resolves only through the
LINEAR_API_KEY GraphQL substrate; without it, the result is unknown.
Invariants
- Tier order is the shared
credential-substrate-precedence contract:
LINEAR_API_KEY + GraphQL first when present and identity-matched, then the
Linear MCP. Do not restate or locally override the ordering here.
- The Linear MCP remains a first-class fallback, not a removed tier: it stays
the substrate whenever
LINEAR_API_KEY is absent, the operation has no GraphQL
adapter, or the token path is failing.
- Identity-match is mandatory on both substrates. A substrate authenticated
against a different Linear organization or team is skipped, never used — that
includes a present-but-wrong
LINEAR_API_KEY, which fails the gate loudly
instead of silently deferring to an authenticated MCP.
- Missing token plus missing MCP is a hard failure naming
LINEAR_API_KEY.
- Mutations send only the fields being changed, matching existing Linear skill
guidance that
save_* style updates should not clobber unrelated fields.